INDEX

Explanations

phrases related to various actions and their consequences

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to damage or consequences

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

anus

-0.60

laus

-0.56

ª

-0.55

cknow

-0.53

giene

-0.52

OPLE

-0.51

Ħ¢

-0.50

rek

-0.49

TAIN

-0.49

ZI

-0.49

POSITIVE LOGITS

 differently

0.79

 nicely

0.65

 everywhere

0.62

lin

0.62

 indistinguishable

0.58

 whereas

0.58

 anyways

0.57

 beautifully

0.57

 automatically

0.57

 MUCH

0.56

Activations Density 1.195%

phrases related to various actions and their consequences

words and phrases related to damage or consequences

No Comments

No Known Activations