INDEX

Explanations

items from a list or series

oai_token-act-pair · gpt-3.5-turbo

sentence-ending punctuation marks, particularly periods

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

emaker

-0.71

nen

-0.70

="#

-0.67

inka

-0.67

bara

-0.66

 cellar

-0.66

iets

-0.65

rou

-0.65

eme

-0.65

iman

-0.65

POSITIVE LOGITS

 respectively

1.33

 Both

1.27

 Together

1.17

 Additionally

1.14

 However

1.11

 These

1.09

 Each

1.09

 They

1.05

 Regardless

1.03

 Their

1.03

Activations Density 0.640%

items from a list or series

sentence-ending punctuation marks, particularly periods

No Comments

No Known Activations