INDEX

Explanations

actions related to creating, producing, and influencing outcomes

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

 msec

-0.64

 fracturing

-0.60

ixties

-0.59

utenberg

-0.58

>>\

-0.56

 haunt

-0.54

(?,

-0.54

 Located

-0.53

ammy

-0.53

 Cruiser

-0.52

POSITIVE LOGITS

ables

0.95

 them

0.92

ments

0.91

 oneself

0.89

 accordingly

0.85

 Them

0.80

 versa

0.80

able

0.79

backs

0.78

 yourself

0.77

Activations Density 0.350%

actions related to creating, producing, and influencing outcomes

No Comments

No Known Activations