INDEX

Explanations

words related to proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

instances of words related to specific geographic or cultural locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Acad

-0.59

\/\/

-0.58

FTC

-0.58

FORMATION

-0.58

JPM

-0.57

 glyph

-0.56

 Malays

-0.54

xual

-0.53

 Vega

-0.53

MJ

-0.52

POSITIVE LOGITS

levard

1.09

apest

1.06

lehem

1.05

pillar

0.94

ause

0.84

abase

0.83

aneers

0.82

rill

0.82

artisan

0.81

wana

0.81

Activations Density 0.114%

words related to proper nouns or names

instances of words related to specific geographic or cultural locations

No Comments

No Known Activations