INDEX

Explanations

phrases related to news articles or reports

oai_token-act-pair · gpt-3.5-turbo

references to specific organizations or entities, particularly those represented by abbreviations or acronyms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

enegger

-0.89

baugh

-0.78

ebted

-0.78

shaw

-0.77

ptin

-0.70

 sidx

-0.67

anamo

-0.67

rador

-0.65

 praise

-0.64

redients

-0.63

POSITIVE LOGITS

DF

1.06

TP

1.00

LC

0.99

Vs

0.98

RP

0.97

TC

0.97

FK

0.97

ZE

0.94

DS

0.94

AC

0.93

Activations Density 0.102%

phrases related to news articles or reports

references to specific organizations or entities, particularly those represented by abbreviations or acronyms

No Comments

No Known Activations