INDEX

Explanations

the word "large" or phrases related to things that are large

oai_token-act-pair · gpt-3.5-turbo

references to the concept of 'large' entities or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çīĪ

-0.78

emy

-0.71

Reviewed

-0.70

ople

-0.70

CB

-0.69

gnu

-0.69

lik

-0.67

utenant

-0.67

forth

-0.67

ception

-0.67

POSITIVE LOGITS

 intestine

1.11

 sized

1.07

 quantities

1.01

 amounts

1.00

 scale

0.99

(>

0.95

 denomination

0.88

 proport

0.87

pox

0.83

 portions

0.81

Activations Density 0.038%

the word "large" or phrases related to things that are large

references to the concept of 'large' entities or quantities

No Comments

No Known Activations