INDEX

Explanations

references to locations or places, specifically those containing the word "Grand"

oai_token-act-pair · gpt-3.5-turbo

references to "Grand" or related geographical or notable entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Downloadha

-1.12

tics

-0.78

PsyNetMessage

-0.71

lihood

-0.70

ylon

-0.69

utics

-0.69

anwhile

-0.69

phrine

-0.66

 chemotherapy

-0.65

 stocks

-0.65

POSITIVE LOGITS

 Prix

1.18

father

1.05

mother

1.00

master

1.00

 Theft

0.96

view

0.95

 Rapids

0.89

pa

0.87

parents

0.85

mist

0.84

Activations Density 0.005%

references to locations or places, specifically those containing the word "Grand"

references to "Grand" or related geographical or notable entities

No Comments

No Known Activations