INDEX

Explanations

references to specific individuals or titles with "arc" in them

oai_token-act-pair · gpt-3.5-turbo

references to the term "arc."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

fulness

-0.84

nder

-0.75

mble

-0.72

lihood

-0.70

hner

-0.68

hower

-0.68

CRIP

-0.68

)=(

-0.67

fully

-0.65

 Trin

-0.65

POSITIVE LOGITS

otics

1.17

aine

0.99

inating

0.90

asm

0.90

inates

0.88

inct

0.88

acia

0.87

issa

0.86

anova

0.85

abulary

0.85

Activations Density 0.021%

references to specific individuals or titles with "arc" in them

references to the term "arc."

No Comments

No Known Activations