INDEX

Explanations

mentions of specific sports teams

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

catentry

-0.82

REDACTED

-0.67

ascript

-0.67

 Predator

-0.66

Ö¼

-0.66

UCT

-0.66

PRES

-0.60

 DRAG

-0.59

 priceless

-0.59

ãĥīãĥ©

-0.57

POSITIVE LOGITS

puff

0.88

ĵĺ

0.84

itzer

0.81

coe

0.80

erville

0.79

emouth

0.79

inki

0.78

erton

0.73

leck

0.71

reau

0.69

Activations Density 5.200%

mentions of specific sports teams

No Comments

No Known Activations