INDEX

Explanations

words related to permissions or usage rights

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly commas

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

 guiName

-0.81

tsky

-0.72

owe

-0.69

._

-0.66

atch

-0.64

 Reported

-0.63

ight

-0.63

agic

-0.63

around

-0.61

Ì

-0.61

POSITIVE LOGITS

etc

1.53

etc

1.35

whatever

0.83

ĪĴ

0.74

0.70

 Mehran

0.64

âĵĺ

0.64

 carbohyd

0.63

 endif

0.63

ect

0.63

Activations Density 0.306%

words related to permissions or usage rights

punctuation marks, particularly commas

No Comments

No Known Activations