INDEX

Explanations

self-reflective questions and statements

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

heny

-0.73

emis

-0.72

Mub

-0.68

 Syndicate

-0.65

microsoft

-0.64

effective

-0.64

rought

-0.63

ritz

-0.63

von

-0.62

iens

-0.62

POSITIVE LOGITS

selves

0.75

 mate

0.73

ħĭ

0.70

åĤ

0.69

çīĪ

0.69

 selves

0.69

 subconscious

0.68

 unconsciously

0.67

 creatively

0.66

ens

0.66

Activations Density 7.732%

self-reflective questions and statements

No Comments

No Known Activations