INDEX

Explanations

words that begin with the letter "S"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ruary

-0.81

abase

-0.70

 innocence

-0.69

nesday

-0.68

rived

-0.62

 Disneyland

-0.60

 Phelps

-0.59

arcity

-0.59

 scient

-0.58

 Barney

-0.58

POSITIVE LOGITS

ami

0.89

uchi

0.86

awa

0.83

kov

0.83

vati

0.78

aka

0.78

ãĤ¿

0.77

cki

0.77

oi

0.77

ichi

0.76

Activations Density 0.062%

words that begin with the letter "S"

No Comments

No Known Activations