INDEX

Explanations

mentions or references to notable figures or political leaders

oai_token-act-pair · gpt-3.5-turbo

the word "at" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Tsukuyomi

-0.75

SPONSORED

-0.72

ppelin

-0.69

vous

-0.65

¥ŀ

-0.64

stocks

-0.63

SER

-0.60

pter

-0.59

æĸ¹

-0.59

gravity

-0.59

POSITIVE LOGITS

abase

1.17

rix

1.15

rice

1.08

oday

1.08

mosp

1.01

hemat

1.00

rices

0.98

hens

0.97

rium

0.95

roph

0.95

Activations Density 0.038%

mentions or references to notable figures or political leaders

the word "at" in various contexts

No Comments

No Known Activations