INDEX

Explanations

phrases related to social or political issues

oai_token-act-pair · gpt-3.5-turbo

conjunctions indicating a relationship or connection between concepts

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

DragonMagazine

-0.80

emi

-0.73

ibi

-0.72

rend

-0.71

ukong

-0.71

ãĤ¤

-0.71

arna

-0.71

ãĤ¨

-0.70

hiro

-0.70

ãĥĥãĥī

-0.68

POSITIVE LOGITS

 thereby

0.92

 other

0.88

 elsewhere

0.85

 assorted

0.82

 others

0.77

 hence

0.76

 preventing

0.75

 consequently

0.75

 thus

0.75

 consequ

0.74

Activations Density 0.322%

phrases related to social or political issues

conjunctions indicating a relationship or connection between concepts

No Comments

No Known Activations