INDEX

Explanations

locations or addresses mentioned in text

oai_token-act-pair · gpt-3.5-turbo

locations and their corresponding addresses or site descriptions

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

ocide

-0.71

thood

-0.69

icter

-0.69

INESS

-0.69

 propagate

-0.68

orians

-0.68

omsky

-0.68

PRESS

-0.66

ãĥĥãĥī

-0.66

sey

-0.66

POSITIVE LOGITS

 downtown

1.05

rium

0.94

 southwest

0.94

 Plaza

0.93

 Gothic

0.92

 Downtown

0.91

 northeast

0.88

 northwest

0.87

 southwestern

0.87

Cyp

0.87

Activations Density 0.398%

locations or addresses mentioned in text

locations and their corresponding addresses or site descriptions

No Comments

No Known Activations