INDEX

Explanations

various names, potentially related to sports teams or individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ãĥ¼ãĤ¯

-0.72

":"/

-0.68

entimes

-0.62

iners

-0.60

rising

-0.60

—

-0.60

algia

-0.60

=\"

-0.60

iculty

-0.59

worldly

-0.59

POSITIVE LOGITS

etc

1.46

etc

1.07

 Moroc

0.91

et

0.86

 Seat

0.83

Osc

0.79

Sod

0.78

Et

0.77

Yor

0.77

Pol

0.76

Activations Density 0.189%

various names, potentially related to sports teams or individuals

proper nouns, particularly names of individuals and places

No Comments

No Known Activations