INDEX

Explanations

questions or statements followed by an answer or explanation

oai_token-act-pair · gpt-3.5-turbo

questions and inquiries within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Notable

-0.82

 endors

-0.70

 "$:/

-0.69

INST

-0.66

eworthy

-0.61

ortment

-0.60

owship

-0.60

 Buff

-0.59

 endorsements

-0.58

 Bers

-0.58

POSITIVE LOGITS

 answer

1.94

 answers

1.91

Answer

1.89

 Answer

1.81

swers

1.63

 answered

1.61

answer

1.50

 answering

1.42

 Answers

1.42

 answ

1.32

Activations Density 0.612%

questions or statements followed by an answer or explanation

questions and inquiries within the text

No Comments

No Known Activations