INDEX

Explanations

a variety of seemingly unrelated time and language-related words, including Latin, French, and German words

oai_token-act-pair · gemini-2.0-flash

per

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

AddTagHelper

-0.68

antMatchers

-0.63

endphp

-0.61

toMatchSnapshot

-0.59

tagHelperRunner

-0.57

 âgées

-0.57

########.

-0.57

fuo

-0.56

 soeur

-0.55

thood

-0.54

POSITIVE LOGITS

 always

1.41

Always

1.35

always

1.34

 Always

1.33

ALWAYS

1.16

 ALWAYS

1.13

 siempre

1.08

 selalu

1.05

 Siempre

1.03

 alway

1.02

Activations Density 0.746%

a variety of seemingly unrelated time and language-related words, including Latin, French, and German words

per

No Comments

No Known Activations