INDEX

Explanations

references to the Pew Research Center

oai_token-act-pair · gpt-3.5-turbo

references to Pew Research surveys and reports

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

 DRAG

-0.65

 chang

-0.63

ACTION

-0.63

 tense

-0.62

 orally

-0.62

abiding

-0.60

 disorderly

-0.59

 ultras

-0.59

Interstitial

-0.58

 Known

-0.57

POSITIVE LOGITS

aukee

1.14

Die

1.04

die

0.91

conn

0.90

Pew

0.88

ersen

0.84

sburg

0.82

sylvania

0.82

pie

0.80

dor

0.79

Activations Density 0.011%

references to the Pew Research Center

references to Pew Research surveys and reports

No Comments

No Known Activations