INDEX

Explanations

financial terms and coding-related words

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

Ĭ±

-0.85

agara

-0.81

 Ukrain

-0.65

 Goodman

-0.65

EGA

-0.65

 Ezek

-0.65

nels

-0.64

rolet

-0.64

 Unsure

-0.63

ensis

-0.63

POSITIVE LOGITS

 instrument

0.76

lishing

0.73

smanship

0.73

 letters

0.71

 aloud

0.71

RAM

0.70

pee

0.70

 memos

0.69

writing

0.69

writ

0.68

Activations Density 0.045%

financial terms and coding-related words

No Comments

No Known Activations