INDEX

Explanations

phrases related to contrasting or specifying different categories or options

oai_token-act-pair · gpt-3.5-turbo

references to relationships and social connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

cki

-0.67

rave

-0.67

WF

-0.57

haw

-0.56

KI

-0.55

itute

-0.55

WD

-0.55

ady

-0.55

Skip

-0.53

RM

-0.52

POSITIVE LOGITS

etc

1.28

etc

1.15

whatever

0.95

ĪĴ

0.82

 blah

0.80

 whatever

0.76

 respectively

0.75

 Allah

0.74

 whichever

0.74

=-=-=-=-

0.71

Activations Density 0.397%

phrases related to contrasting or specifying different categories or options

references to relationships and social connections

No Comments

No Known Activations