INDEX

Explanations

examples and explanations in the form of "e.g." (for example)

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'g'

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

 haun

-0.71

SPONSORED

-0.68

Cause

-0.66

DEBUG

-0.65

 heats

-0.63

 tranquil

-0.61

 merry

-0.60

 captures

-0.60

 repay

-0.59

 psychiat

-0.59

POSITIVE LOGITS

raphics

0.88

.,

0.85

aminer

0.83

asp

0.79

ascript

0.76

ardless

0.74

raham

0.73

aws

0.73

ree

0.71

viously

0.71

Activations Density 0.014%

examples and explanations in the form of "e.g." (for example)

occurrences of the letter 'g'

No Comments

No Known Activations