INDEX

Explanations

acronyms and abbreviations that include 'PP' with varying levels of specificity

oai_token-act-pair · gpt-3.5-turbo

references to political party affiliations or related acronyms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

flies

-0.97

puter

-0.78

gers

-0.78

 Plague

-0.73

sbm

-0.73

mberg

-0.71

ãĤ¤ãĥĪ

-0.71

pole

-0.71

 quot

-0.70

ebted

-0.70

POSITIVE LOGITS

olicy

1.15

ublic

1.12

odcast

1.02

PP

0.95

ERC

0.92

eter

0.92

IX

0.92

arser

0.91

rint

0.88

EED

0.87

Activations Density 0.023%

acronyms and abbreviations that include 'PP' with varying levels of specificity

references to political party affiliations or related acronyms

No Comments

No Known Activations