INDEX

Explanations

names and terms related to political figures

oai_token-act-pair · gpt-3.5-turbo

words with "ar" or "un" in various forms

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

nesday

-0.76

ancial

-0.68

ankind

-0.67

rongh

-0.65

ascus

-0.65

glers

-0.63

wcs

-0.63

etheless

-0.59

 sake

-0.59

awed

-0.58

POSITIVE LOGITS

wine

0.70

itect

0.70

inian

0.69

aston

0.65

agos

0.64

tes

0.63

ondo

0.62

ICT

0.62

Rah

0.62

omaly

0.62

Activations Density 0.069%

names and terms related to political figures

words with "ar" or "un" in various forms

No Comments

No Known Activations