INDEX

Explanations

the word "Kal" with varying levels of activation strength

oai_token-act-pair · gpt-3.5-turbo

references to a specific individual named Kalashnikov

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

ãĥ¼ãĥĨãĤ£

-0.92

ãģį

-0.71

IBLE

-0.65

AGE

-0.64

ORTS

-0.63

çĶŁ

-0.62

UCT

-0.61

 halftime

-0.61

 degrade

-0.60

åĳ

-0.60

POSITIVE LOGITS

adesh

1.27

amaz

1.26

arov

1.01

endar

1.00

inda

0.97

ibr

0.97

iev

0.96

ita

0.95

endars

0.94

tering

0.93

Activations Density 0.018%

the word "Kal" with varying levels of activation strength

references to a specific individual named Kalashnikov

No Comments

No Known Activations