INDEX

Explanations

phrases starting with "Our"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Our."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

CENT

-0.66

``(

-0.66

liest

-0.64

ambers

-0.64

LSD

-0.63

quote

-0.61

 externalToEVAOnly

-0.61

–

-0.61

cum

-0.60

conom

-0.60

POSITIVE LOGITS

selves

1.44

own

0.99

¥ŀ

0.98

self

0.93

anmar

0.92

 adversary

0.83

cyclopedia

0.83

 adversaries

0.82

 ourselves

0.78

 fearless

0.77

Activations Density 0.049%

phrases starting with "Our"

instances of the word "Our."

No Comments

No Known Activations