INDEX

Explanations

references to a specific collection or group of items

oai_token-act-pair · gpt-3.5-turbo

references to collections or groups of items

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

issance

-0.81

ibly

-0.68

IBLE

-0.66

Fight

-0.64

 sincerity

-0.63

 tears

-0.63

 distingu

-0.62

perse

-0.62

ãĥĨãĤ£

-0.60

irtual

-0.59

POSITIVE LOGITS

offs

1.08

tle

1.03

list

0.88

ters

0.88

eq

0.87

ups

0.86

ter

0.85

chell

0.82

lists

0.82

tering

0.80

Activations Density 0.041%

references to a specific collection or group of items

references to collections or groups of items

No Comments

No Known Activations