INDEX

Explanations

phrases related to numbers, measurements, and statistics

oai_token-act-pair · gpt-3.5-turbo

special characters and symbols in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 gist

-0.72

 trainers

-0.68

udeb

-0.68

 trainer

-0.67

 sidel

-0.64

 Digest

-0.63

 posture

-0.62

 bystand

-0.62

 nucleus

-0.62

 recomm

-0.62

POSITIVE LOGITS

ï¸ı

1.41

Ëľ

0.98

ï¸

0.89

âĪ

0.85

Ãī

0.84

nai

0.82

Â¯

0.82

Â±

0.82

Â£

0.82

ÃĽ

0.81

Activations Density 0.054%

phrases related to numbers, measurements, and statistics

special characters and symbols in the text

No Comments

No Known Activations