INDEX

Explanations

numeric ranges or spans

oai_token-act-pair · gpt-3.5-turbo

references to various types of ranges

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

Congratulations

-0.70

thank

-0.68

Spons

-0.68

ãģ¨

-0.67

Tickets

-0.67

mone

-0.66

Tid

-0.65

Untitled

-0.64

Ed

-0.64

 ARTICLE

-0.64

POSITIVE LOGITS

 range

4.00

 ranges

2.96

 Range

2.67

range

2.59

Range

2.02

 ranged

1.91

 variety

1.70

 spectrum

1.52

 ranging

1.46

ranged

1.28

Activations Density 0.014%

numeric ranges or spans

references to various types of ranges

No Comments

No Known Activations