INDEX

Explanations

phrases expressing admiration or astonishment

oai_token-act-pair · gpt-3.5-turbo

questions or inquiries regarding methods or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

isher

-0.67

 Goth

-0.63

agonists

-0.59

ãĤ«

-0.57

quist

-0.57

 Mercenary

-0.56

Die

-0.56

ãĥ¼ãĥ

-0.56

)]

-0.56

 Guer

-0.56

POSITIVE LOGITS

soever

1.04

HCR

0.84

ever

0.78

paio

0.76

beit

0.75

ricanes

0.72

 nomine

0.71

 MUCH

0.69

itzer

0.69

 much

0.68

Activations Density 0.060%

phrases expressing admiration or astonishment

questions or inquiries regarding methods or processes

No Comments

No Known Activations