INDEX

Explanations

research findings and experimental results

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

erness

-0.74

agine

-0.72

tones

-0.71

conservancy

-0.69

tera

-0.65

kov

-0.65

thur

-0.65

vette

-0.65

otin

-0.65

nt

-0.63

POSITIVE LOGITS

iveness

0.89

ainer

0.86

ively

0.83

ivity

0.81

results

0.77

antly

0.75

 thereof

0.74

 outcome

0.72

 results

0.72

ient

0.70

Activations Density 1.945%

research findings and experimental results

No Comments

No Known Activations