INDEX

Explanations

locations specified as cities or states

oai_token-act-pair · gpt-3.5-turbo

geographical locations and associated punctuation

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

thood

-0.94

emonic

-0.80

odic

-0.76

uture

-0.73

natureconservancy

-0.72

 formulations

-0.71

OGR

-0.69

asers

-0.68

onym

-0.67

utic

-0.67

POSITIVE LOGITS

VA

0.86

 Calif

0.78

 Moroc

0.77

NY

0.76

 Mountains

0.75

IL

0.75

 Colo

0.74

KY

0.74

opolis

0.74

TN

0.72

Activations Density 0.065%

locations specified as cities or states

geographical locations and associated punctuation

No Comments

No Known Activations