INDEX

Explanations

javascript code

oai_token-act-pair · gemini-2.0-flash

programming language syntax or code structures

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

say "from"

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

})));

-0.68

webElement

-0.63

SourceChecksum

-0.59

SharedCtor

-0.52

oo

-0.51

 hearers

-0.48

go

-0.48

dl

-0.47

AntiForgeryToken

-0.47

.]

-0.47

POSITIVE LOGITS

 CreateTagHelper

0.84

databind

0.69

ंदीखरीदारी

0.69

Vidite

0.64

yelidikan

0.61

 يتيمه

0.61

 חיצוניים

0.60

 saites

0.60

rrggbb

0.59

INR

0.58

Activations Density 0.665%

javascript code

programming language syntax or code structures

say "from"

No Comments

No Known Activations