INDEX

Explanations

words that signify awakening or calls to action

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

 eliminated

-0.73

©¶æ

-0.66

 foremost

-0.65

 trained

-0.63

Dialogue

-0.59

 contracted

-0.59

undo

-0.59

 improperly

-0.59

edly

-0.58

 qualified

-0.58

POSITIVE LOGITS

ings

0.88

aneers

0.84

pic

0.81

ocratic

0.79

uations

0.78

iery

0.76

iable

0.75

aways

0.75

creen

0.75

outs

0.74

Activations Density 0.020%

words that signify awakening or calls to action

No Comments

No Known Activations