INDEX

Explanations

references to the name "Mika"

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

gob

-0.83

 corrid

-0.81

iaries

-0.80

 glim

-0.80

shire

-0.79

bledon

-0.79

chester

-0.76

bidden

-0.76

entially

-0.76

matically

-0.75

POSITIVE LOGITS

ishi

0.89

ika

0.87

qt

0.84

emia

0.83

ibu

0.83

ikk

0.82

ppa

0.81

ulic

0.81

uchi

0.81

Ã±

0.79

Activations Density 0.007%

references to the name "Mika"

No Comments

No Known Activations