INDEX

Explanations

number and text patterns like protocols and settings

oai_token-act-pair · gpt-3.5-turbo

numerical values and specific identifiers

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

ande

-0.80

cott

-0.72

uran

-0.70

-0.69

antine

-0.68

 Dane

-0.68

CAM

-0.67

 Gott

-0.67

anian

-0.66

 belt

-0.66

POSITIVE LOGITS

1.54

º

1.03

0.99

0.95

0.89

0.88

0.87

Activations Density 0.185%

number and text patterns like protocols and settings

numerical values and specific identifiers

No Comments

No Known Activations