INDEX

Explanations

mentions of specific names or terms, like "ron" and "ape"

oai_token-act-pair · gpt-3.5-turbo

proper nouns and significant numerical values related to organizations or products

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-1.09

YA

-0.92

¥µ

-0.92

GoldMagikarp

-0.88

yah

-0.87

roxy

-0.85

»Ĵ

-0.81

 Parables

-0.79

YN

-0.78

yrinth

-0.77

POSITIVE LOGITS

co

0.90

0.87

CO

0.83

 Ange

0.77

CO

0.75

ãĤ¬

0.75

0.70

 oblig

0.69

 Hoff

0.69

 mail

0.68

Activations Density 0.297%

mentions of specific names or terms, like "ron" and "ape"

proper nouns and significant numerical values related to organizations or products

No Comments

No Known Activations