INDEX

Explanations

mentions of specific job titles and company names

oai_token-act-pair · gpt-3.5-turbo

references to individuals associated with leadership and authoritative roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

isphere

-0.81

hay

-0.79

bilt

-0.76

 Strongh

-0.76

rist

-0.74

adelphia

-0.74

rists

-0.74

 Morty

-0.72

 barn

-0.72

orth

-0.70

POSITIVE LOGITS

Tu

1.77

Pu

1.73

Tu

1.68

Du

1.65

Du

1.60

Mu

1.57

Nu

1.54

Hu

1.54

Vu

1.52

Ku

1.50

Activations Density 0.322%

mentions of specific job titles and company names

references to individuals associated with leadership and authoritative roles

No Comments

No Known Activations