INDEX

Explanations

mentions of specific individuals involved in political controversies or crimes

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

 laps

-0.66

 Clicker

-0.66

FACE

-0.65

 smarter

-0.62

nesday

-0.60

é¾įå¥ĳå£«

-0.59

 programmed

-0.57

 herein

-0.57

glers

-0.56

 Replay

-0.56

POSITIVE LOGITS

igans

1.18

thal

1.00

igan

0.98

azard

0.93

ov

0.91

istic

0.88

agan

0.88

istan

0.87

ovember

0.86

irez

0.86

Activations Density 0.026%

mentions of specific individuals involved in political controversies or crimes

No Comments

No Known Activations