INDEX

Explanations

locations or specific bases

oai_token-act-pair · gpt-3.5-turbo

references to military or operational locations and activities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oeuv

-0.69

obs

-0.68

ifter

-0.65

 explanations

-0.63

idences

-0.62

vous

-0.61

eye

-0.61

comments

-0.60

ensen

-0.59

dash

-0.59

POSITIVE LOGITS

 north

0.98

 northeast

0.95

 northwest

0.95

 south

0.93

 southwest

0.89

 Nottingham

0.89

 east

0.88

 Perth

0.88

 southeast

0.88

 west

0.87

Activations Density 0.484%

locations or specific bases

references to military or operational locations and activities

No Comments

No Known Activations