INDEX

Explanations

words related to countries and organizations

oai_token-act-pair · gpt-3.5-turbo

references to nations, countries, and organizations in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

prem

-0.77

utenberg

-0.75

aund

-0.71

hai

-0.71

 Supplemental

-0.70

ilon

-0.70

ounded

-0.69

ritz

-0.69

igers

-0.66

pread

-0.65

POSITIVE LOGITS

 whatsoever

1.27

 imaginable

1.24

 except

0.96

 conceivable

0.95

soever

0.90

 besides

0.90

 anywhere

0.86

 else

0.81

else

0.81

 EVER

0.76

Activations Density 0.220%

words related to countries and organizations

references to nations, countries, and organizations in various contexts

No Comments

No Known Activations