INDEX

Explanations

mentions of the name "Jay" with a strong emphasis on "Jay" as the name activates the neuron significantly

oai_token-act-pair · gpt-3.5-turbo

the name "Jay" in various contexts related to the individual or character

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ITIES

-0.80

iture

-0.78

milo

-0.72

idad

-0.71

ENTION

-0.68

htaking

-0.66

ities

-0.66

ITY

-0.66

iments

-0.65

ational

-0.65

POSITIVE LOGITS

hawks

1.28

hawk

1.17

walking

1.14

den

0.96

haw

0.96

lon

0.94

bird

0.91

pee

0.90

Jay

0.88

len

0.86

Activations Density 0.025%

mentions of the name "Jay" with a strong emphasis on "Jay" as the name activates the neuron significantly

the name "Jay" in various contexts related to the individual or character

No Comments

No Known Activations