INDEX

Explanations

categories or classification terms

oai_token-act-pair · gpt-3.5-turbo

references to categories or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

zos

-0.68

OUGH

-0.66

arbon

-0.65

ONEY

-0.65

anoia

-0.64

rets

-0.63

arie

-0.62

 anew

-0.62

 reconnect

-0.61

ourn

-0.60

POSITIVE LOGITS

 category

3.68

 categories

2.62

category

2.39

 Category

2.39

Category

2.02

 Categories

1.84

 classification

1.67

 genre

1.45

 categor

1.40

ategory

1.36

Activations Density 0.012%

categories or classification terms

references to categories or classifications

No Comments

No Known Activations