INDEX

Explanations

copyright details and attributions in text

oai_token-act-pair · gpt-3.5-turbo

phrases indicating authorship or attribution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

apy

-0.67

naire

-0.66

hall

-0.64

aviour

-0.63

 tests

-0.61

uality

-0.60

 tested

-0.60

 halls

-0.60

amiya

-0.60

POSITIVE LOGITS

 STATS

1.10

KO

0.86

 Bite

0.80

KR

0.78

 pione

0.76

 PEOPLE

0.75

 Rossi

0.72

WR

0.72

KH

0.72

 Inquis

0.71

Activations Density 0.056%

copyright details and attributions in text

phrases indicating authorship or attribution

No Comments

No Known Activations