INDEX

Explanations

the word 'parked'

oai_token-act-pair · gpt-4-turbo

references to vehicles being parked

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "parked" or related terms indicating stationary vehicles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Flavoring

-1.02

vernment

-0.80

é¾įåĸļå£«

-0.74

é¾įå¥ĳå£«

-0.74

adeon

-0.70

bit

-0.70

astical

-0.69

externalActionCode

-0.69

ï¸ı

-0.69

mp

-0.66

POSITIVE LOGITS

 parked

1.12

 parking

0.72

wagon

0.72

 brake

0.71

 Slug

0.71

DeL

0.71

 Garage

0.70

 buggy

0.70

conservancy

0.69

atoon

0.69

Activations Density 0.003%

the word 'parked'

references to vehicles being parked

occurrences of the word "parked" or related terms indicating stationary vehicles

No Comments

No Known Activations