INDEX

Explanations

terms related to professions or job titles

oai_token-act-pair · gpt-3.5-turbo

roles or titles associated with professional or organizational settings

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

izoph

-0.81

brew

-0.74

earable

-0.70

;;;;;;;;;;;;

-0.70

LAN

-0.69

border

-0.66

PASS

-0.66

CONT

-0.65

shown

-0.63

warming

-0.62

POSITIVE LOGITS

 extraord

1.05

esses

0.84

rors

0.81

 specializing

0.81

yssey

0.73

 accredited

0.72

ams

0.71

 Panasonic

0.70

ateurs

0.70

 hired

0.69

Activations Density 0.324%

terms related to professions or job titles

roles or titles associated with professional or organizational settings

No Comments

No Known Activations