INDEX

Explanations

phrases related to instructions or guidelines

oai_token-act-pair · gpt-3.5-turbo

statements related to rules and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

wake

-0.79

roit

-0.74

Americans

-0.73

ahu

-0.71

alky

-0.70

aud

-0.66

Initialized

-0.65

ocrats

-0.64

atlantic

-0.62

lie

-0.61

POSITIVE LOGITS

 also

1.04

 optional

0.97

 plenty

0.94

 currently

0.89

 ALSO

0.85

 lots

0.81

 however

0.79

 optionally

0.79

 adjustable

0.79

no

0.78

Activations Density 0.155%

phrases related to instructions or guidelines

statements related to rules and conditions

No Comments

No Known Activations