INDEX

Explanations

mathematical symbols and related expressions

oai_token-act-pair · gpt-3.5-turbo

references to locations or geographical entities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Confederation

-0.80

izabeth

-0.75

 Chambers

-0.58

iott

-0.58

 breathing

-0.58

 Cannon

-0.58

ight

-0.57

enko

-0.57

 Receiver

-0.56

otiation

-0.55

POSITIVE LOGITS

Ag

0.78

AIDS

0.78

Hy

0.74

Pak

0.73

Mex

0.72

wikipedia

0.72

Ger

0.71

su

0.71

gyn

0.71

Cong

0.71

Activations Density 0.128%

mathematical symbols and related expressions

references to locations or geographical entities

No Comments

No Known Activations