INDEX

Explanations

verbs related to necessity or requirement

oai_token-act-pair · gpt-3.5-turbo

phrases indicating conditionality or uncertainty

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ASAP

-0.79

ciation

-0.75

enegger

-0.73

BSD

-0.72

Bam

-0.71

fund

-0.70

udeb

-0.67

 Showdown

-0.66

 Denis

-0.65

 Compatibility

-0.61

POSITIVE LOGITS

 glimps

0.88

 mistaken

0.88

 unconsciously

0.82

hemer

0.80

pmwiki

0.79

 downright

0.79

entimes

0.79

times

0.78

 overlooked

0.78

 subconscious

0.74

Activations Density 0.325%

verbs related to necessity or requirement

phrases indicating conditionality or uncertainty

No Comments

No Known Activations