INDEX

Explanations

quotes or reported statements in a news context

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

 sidx

-0.75

imposed

-0.74

 ILCS

-0.73

adesh

-0.71

elsh

-0.69

mun

-0.65

Interstitial

-0.65

mite

-0.65

aband

-0.65

racted

-0.65

POSITIVE LOGITS

us

1.23

tale

1.18

me

1.14

him

1.02

ingly

0.98

 reporters

0.90

 them

0.83

 listeners

0.81

 viewers

0.78

 passers

0.76

Activations Density 1.571%

quotes or reported statements in a news context

No Comments

No Known Activations