INDEX

Explanations

mentions of detaining or related actions

oai_token-act-pair · gpt-3.5-turbo

terms related to detention or detainment

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ocene

-0.98

manship

-0.78

ammy

-0.71

raviolet

-0.69

 Myth

-0.67

 Awakens

-0.65

 nomine

-0.64

externalActionCode

-0.63

Myth

-0.62

ħĭ

-0.62

POSITIVE LOGITS

ention

1.06

det

1.05

roit

0.96

achable

0.94

ailed

0.90

ried

0.87

rans

0.82

ainer

0.80

ourn

0.79

ered

0.79

Activations Density 0.006%

mentions of detaining or related actions

terms related to detention or detainment

No Comments

No Known Activations