INDEX

Explanations

specific terms and symbols related to data or metrics

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

NCT

-0.73

natureconservancy

-0.72

 soils

-0.71

alach

-0.66

reads

-0.65

comings

-0.64

ŃĶ

-0.64

 Transformation

-0.63

©¶æ

-0.63

eatures

-0.62

POSITIVE LOGITS

eus

0.65

izon

0.65

lich

0.65

bard

0.64

arov

0.62

 sidx

0.62

ius

0.61

hor

0.61

point

0.61

 against

0.60

Activations Density 0.001%

specific terms and symbols related to data or metrics

No Comments

No Known Activations