INDEX

Explanations

numerical values represented in dollars, pounds, or quantities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating quantities greater than a specified number

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Finder

-0.72

 derog

-0.69

NEY

-0.68

 Bomber

-0.65

ilic

-0.65

ãĤ¼ãĤ¦ãĤ¹

-0.62

 Pioneer

-0.62

Ô

-0.60

oris

-0.60

OSP

-0.59

POSITIVE LOGITS

whelming

0.87

capacity

0.80

lyak

0.79

represent

0.76

arching

0.71

fif

0.71

iw

0.69

perties

0.68

atos

0.67

Activations Density 0.055%

numerical values represented in dollars, pounds, or quantities

phrases indicating quantities greater than a specified number

No Comments

No Known Activations