INDEX

Explanations

references to academic disciplines, particularly in the humanities and social sciences, such as philosophy, history, and literature

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

•Layer 6 UMAP region: Mixed in middle - local

No Comments

Negative Logits

å¥³

-0.81

ells

-0.80

esty

-0.78

cue

-0.74

ilee

-0.71

ookie

-0.71

rake

-0.71

bang

-0.69

bring

-0.69

elight

-0.68

POSITIVE LOGITS

ophical

1.32

ophers

0.96

ophe

0.87

ophy

0.87

opher

0.87

 philosopher

0.83

lectic

0.81

otle

0.79

 philosophy

0.78

 philosophers

0.77

Activations Density 10.137%

references to academic disciplines, particularly in the humanities and social sciences, such as philosophy, history, and literature

No Comments

No Known Activations