INDEX

Explanations

Java code syntax

oai_token-act-pair · gemini-2.0-flash

programming keywords and syntax

np_token-act-pair-logits · gpt-4o-mini

(

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Kaieteur

-0.69

aclk

-0.52

satellite

-0.50

{{/

-0.50

Papers

-0.49

AGUE

-0.48

 发表于

-0.48

Zus

-0.48

werfen

-0.48

ELINES

-0.47

POSITIVE LOGITS

const

0.65

 فريبيس

0.63

 greateſt

0.62

 ―――――

0.59

int

0.59

 doubtnut

0.56

Iden

0.56

 صوتيه

0.56

 iſt

0.55

TextWatcher

0.55

Activations Density 3.055%

Java code syntax

programming keywords and syntax

(

No Comments

No Known Activations