INDEX

Explanations

proper names

oai_token-act-pair · gpt-3.5-turbo

numerical or statistical data presentations

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

 increment

-0.83

 singles

-0.80

 smugglers

-0.80

tro

-0.79

 spir

-0.78

 stigmat

-0.77

 unfold

-0.76

 contrasting

-0.74

 highlight

-0.74

 treat

-0.74

POSITIVE LOGITS

Offline

1.67

Executive

1.61

Member

1.60

Born

1.59

Premium

1.58

Senior

1.57

Legendary

1.56

Director

1.55

Joined

1.52

Age

1.50

Activations Density 0.170%

proper names

numerical or statistical data presentations

No Comments

No Known Activations