INDEX

Explanations

mentions of the word 'ice'

oai_token-act-pair · gpt-3.5-turbo

references to ice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

anan

-0.77

ancial

-0.74

nesday

-0.73

=-=-=-=-=-=-=-=-

-0.71

enance

-0.70

edy

-0.69

nen

-0.69

QR

-0.67

merce

-0.66

FFFF

-0.64

POSITIVE LOGITS

breaker

1.32

breakers

1.28

cream

1.24

 cream

1.23

 rink

1.09

pick

1.00

 Cream

0.99

berg

0.99

caps

0.94

 skating

0.94

Activations Density 0.025%

mentions of the word 'ice'

references to ice

No Comments

No Known Activations