INDEX

Explanations

sentences containing questions

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

yo

-0.60

knife

-0.56

folk

-0.56

worldly

-0.53

gran

-0.53

breakers

-0.53

 mete

-0.53

 Sparrow

-0.53

fam

-0.53

hol

-0.52

POSITIVE LOGITS

interstitial

0.82

 guiIcon

0.81

Interstitial

0.78

 toggle

0.76

 Loading

0.76

push

0.65

 Invalid

0.65

 isEnabled

0.65

 sclerosis

0.65

},"

0.64

Activations Density 1.453%

sentences containing questions

No Comments

No Known Activations