INDEX

Explanations

phrases indicating lack of correlation or connection between two entities

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the disconnection or irrelevance of subjects to certain issues

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

atures

-0.68

don

-0.65

pa

-0.63

theless

-0.63

pret

-0.63

ŀ

-0.62

TR

-0.62

ricted

-0.61

rique

-0.60

©¶æ¥µ

-0.60

POSITIVE LOGITS

ozy

0.77

pez

0.67

SEO

0.66

itaire

0.65

uate

0.64

omsday

0.64

actic

0.63

uating

0.62

berman

0.62

xx

0.62

Activations Density 0.038%

phrases indicating lack of correlation or connection between two entities

phrases emphasizing the disconnection or irrelevance of subjects to certain issues

No Comments

No Known Activations