INDEX

Explanations

names of places or people

oai_token-act-pair · gpt-3.5-turbo

specific initials or acronyms associated with locations or events

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

idium

-1.09

Domin

-0.82

ãĥĩãĤ£

-0.78

ira

-0.77

inator

-0.77

Isa

-0.75

JD

-0.73

Ñ

-0.72

ila

-0.72

ipel

-0.71

POSITIVE LOGITS

web

0.85

web

0.73

gow

0.73

ews

0.73

 Chow

0.71

 watch

0.71

 Greens

0.71

0.70

 Care

0.69

 Work

0.68

Activations Density 0.351%

names of places or people

specific initials or acronyms associated with locations or events

No Comments

No Known Activations