INDEX

Explanations

terms related to cognitive function and performance

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

wives

-0.83

Mex

-0.73

EGA

-0.72

encer

-0.71

olicited

-0.69

ourced

-0.69

FORE

-0.69

Khe

-0.68

arov

-0.66

export

-0.66

POSITIVE LOGITS

 disson

1.39

enh

1.09

 impairment

1.01

 faculties

1.00

 behavioural

0.95

 enhancement

0.94

 behavi

0.88

 impair

0.85

 behavioral

0.84

 enhancing

0.84

Activations Density 0.025%

terms related to cognitive function and performance

No Comments

No Known Activations