INDEX

Explanations

instances where something exceeds expectations or is particularly noteworthy

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "even."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

rend

-0.89

aim

-0.88

asy

-0.69

ync

-0.68

unity

-0.68

ugal

-0.67

ample

-0.66

========

-0.63

Exit

-0.63

hammad

-0.62

POSITIVE LOGITS

 remotely

0.91

 though

0.86

tho

0.85

handedly

0.83

 joked

0.78

 briefly

0.76

 indirectly

0.73

 entertained

0.69

 retweet

0.68

handed

0.68

Activations Density 0.053%

instances where something exceeds expectations or is particularly noteworthy

occurrences of the word "even."

No Comments

No Known Activations