INDEX

Explanations

phrases related to placing oneself in vulnerable or dangerous situations

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

querque

-0.70

imar

-0.69

llo

-0.69

glers

-0.69

heim

-0.67

orf

-0.65

lli

-0.65

catentry

-0.65

uum

-0.65

nos

-0.63

POSITIVE LOGITS

 behalf

0.60

 imitation

0.59

 righteousness

0.59

 nomine

0.59

 theirs

0.57

 Shutterstock

0.57

 deeds

0.55

 stake

0.55

 whichever

0.54

 jeopardy

0.54

Activations Density 0.331%

phrases related to placing oneself in vulnerable or dangerous situations

No Comments

No Known Activations