INDEX

Explanations

mentions of customization and personalized items

oai_token-act-pair · gpt-3.5-turbo

references to customization and personalized products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

common

-0.79

here

-0.75

·

-0.73

quart

-0.71

gdala

-0.70

 CrossRef

-0.68

went

-0.68

á½

-0.66

down

-0.66

trump

-0.64

POSITIVE LOGITS

isable

1.90

izations

1.80

izable

1.70

ised

1.61

isation

1.57

isations

1.53

arily

1.44

ization

1.38

izing

1.35

ized

1.33

Activations Density 0.042%

mentions of customization and personalized items

references to customization and personalized products or services

No Comments

No Known Activations