INDEX

Explanations

references to web domains containing "ca" followed by a string of numbers

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "ca"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

schild

-0.83

rats

-0.76

states

-0.76

mble

-0.74

 GOODMAN

-0.74

pocket

-0.73

enegger

-0.72

leness

-0.70

PDATE

-0.69

tle

-0.69

POSITIVE LOGITS

ption

1.19

esar

1.05

utical

0.92

ution

0.86

ffe

0.85

UTION

0.85

iba

0.79

qua

0.79

zza

0.78

hedral

0.77

Activations Density 0.010%

references to web domains containing "ca" followed by a string of numbers

occurrences of the substring "ca"

No Comments

No Known Activations