INDEX

Explanations

mentions and references to the word "gold."

oai_token-act-pair · gpt-3.5-turbo

references to the word 'gold' and its related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ATIONS

-0.80

ROR

-0.78

zee

-0.78

ally

-0.73

========

-0.73

 Consent

-0.71

 Alive

-0.69

 reperto

-0.68

 Homeless

-0.66

 Stras

-0.65

POSITIVE LOGITS

vertisement

1.20

smith

1.05

 medal

1.02

 coins

1.00

fish

0.96

 medals

0.89

stone

0.88

 jewelry

0.88

mine

0.88

mund

0.86

Activations Density 0.017%

mentions and references to the word "gold."

references to the word 'gold' and its related contexts

No Comments

No Known Activations