INDEX

Explanations

references to individuals involved in controversies or allegations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

 envy

-0.64

isters

-0.59

ICLE

-0.58

ificial

-0.58

 istg

-0.57

ACTED

-0.54

oleon

-0.54

uador

-0.53

icial

-0.52

 pity

-0.51

POSITIVE LOGITS

chuk

0.78

idge

0.75

gow

0.71

yk

0.70

gat

0.66

bottom

0.66

dal

0.64

kov

0.62

bee

0.62

yi

0.61

Activations Density 0.041%

references to individuals involved in controversies or allegations

No Comments

No Known Activations