INDEX

Explanations

sentences ending in a period

oai_token-act-pair · gpt-3.5-turbo

occurrences of sentences that express declining to provide comments

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

 tremend

-1.01

 bully

-0.92

 imagination

-0.85

 scenery

-0.81

 unstoppable

-0.81

 beaut

-0.81

 revol

-0.81

 amazing

-0.81

 metic

-0.80

 gorge

-0.80

POSITIVE LOGITS

 Additionally

1.35

 However

1.25

 Previously

1.23

<|endoftext|>

1.20

 Officials

1.16

 According

1.16

 Alternatively

1.14

 Presumably

1.12

 Afterwards

1.12

 Notably

1.11

Activations Density 0.742%

sentences ending in a period

occurrences of sentences that express declining to provide comments

No Comments

No Known Activations