INDEX

Explanations

statements or comments made by notable individuals

oai_token-act-pair · gpt-3.5-turbo

phrases related to advocacy and statements made by individuals in positions of authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

xa

-0.70

psy

-0.70

 stabilization

-0.62

 totality

-0.59

 physical

-0.59

)}

-0.59

 brill

-0.58

 scaven

-0.58

 beginners

-0.58

Subject

-0.58

POSITIVE LOGITS

Jr

0.95

Sr

0.77

uty

0.76

QC

0.76

icer

0.75

ogun

0.74

thouse

0.71

herty

0.70

 presiding

0.69

«ĺ

0.69

Activations Density 0.754%

statements or comments made by notable individuals

phrases related to advocacy and statements made by individuals in positions of authority

No Comments

No Known Activations