INDEX

Explanations

instances of the word "scan"

oai_token-act-pair · gpt-3.5-turbo

terms related to scanning technology or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Cind

-0.69

ofi

-0.61

Aid

-0.60

agne

-0.60

 defe

-0.59

 impunity

-0.59

 pengu

-0.59

emort

-0.58

doms

-0.57

acia

-0.56

POSITIVE LOGITS

lator

1.16

 scans

1.09

 scan

1.04

lations

1.01

ning

0.92

 scanners

0.89

 scanning

0.89

lation

0.88

 scanned

0.84

QR

0.83

Activations Density 0.023%

instances of the word "scan"

terms related to scanning technology or processes

No Comments

No Known Activations