INDEX

Explanations

sentences with a recurring structure of introducing a topic followed by a statement or description

oai_token-act-pair · gpt-3.5-turbo

punctuation, specifically periods at the end of sentences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hug

-0.82

 portrait

-0.77

 advis

-0.75

 silent

-0.73

 dictate

-0.70

 administrator

-0.69

 withd

-0.69

 trusted

-0.69

 posture

-0.69

lap

-0.68

POSITIVE LOGITS

 However

1.28

 Unfortunately

1.25

 Additionally

1.25

 Interestingly

1.18

 Meanwhile

1.18

 Similarly

1.17

 Fortunately

1.15

 Luckily

1.14

 Afterwards

1.13

 Furthermore

1.13

Activations Density 0.615%

sentences with a recurring structure of introducing a topic followed by a statement or description

punctuation, specifically periods at the end of sentences

No Comments

No Known Activations