INDEX

Explanations

phrases that indicate the beginning of an action or event

oai_token-act-pair · gpt-4o-mini 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

itsch

-0.88

cedented

-0.76

vertisement

-0.70

abyte

-0.68

mens

-0.68

ilty

-0.66

hooting

-0.66

holding

-0.66

ombat

-0.65

igent

-0.64

POSITIVE LOGITS

 anew

0.95

strap

0.71

XI

0.70

points

0.70

 salaries

0.65

 point

0.65

ribune

0.64

 Gutenberg

0.61

 inference

0.59

 fires

0.58

Activations Density 0.043%

phrases that indicate the beginning of an action or event

No Comments

No Known Activations