INDEX

Explanations

dates or significant events mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

colons and punctuation marks indicating lists or segments in text

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

undai

-0.77

 destro

-0.73

 manif

-0.72

nesday

-0.71

 tremend

-0.67

 livest

-0.66

 undermin

-0.66

 misunder

-0.65

mble

-0.65

avorite

-0.64

POSITIVE LOGITS

 Provided

0.79

 Join

0.74

 âĨĳ

0.68

Associated

0.67

 Researchers

0.67

 âĺħ

0.67

YES

0.65

][

0.65

 Latest

0.64

 http

0.64

Activations Density 0.116%

dates or significant events mentioned in the text

colons and punctuation marks indicating lists or segments in text

No Comments

No Known Activations