INDEX

Explanations

phrases involving the word "to" indicating intention or direction

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

grain

-0.72

sbm

-0.71

interstitial

-0.59

recated

-0.59

llo

-0.58

yg

-0.57

 guessed

-0.57

 exited

-0.56

 contradicted

-0.56

 froze

-0.56

POSITIVE LOGITS

ggles

1.02

iling

0.95

pload

0.93

 maximize

0.85

asting

0.83

ilet

0.80

wered

0.80

 extinction

0.77

ilings

0.74

asts

0.74

Activations Density 0.112%

phrases involving the word "to" indicating intention or direction

No Comments

No Known Activations