INDEX

Explanations

characters or symbols within the text

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

Code-related special characters

np_acts-logits-general · gemini-2.0-flash

`@covers` or `thereof`

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AsUp

-1.01

writeFieldEnd

-0.92

 initComponents

-0.91

 JpaRepository

-0.91

 photolibrary

-0.90

<",

-0.89

LLocation

-0.88

 aDecoder

-0.88

 itſelf

-0.87

ruptedException

-0.87

POSITIVE LOGITS

0.57

<bos>

0.49

исленность

0.48

<strong>

0.47

www

0.43

↵

0.43

((

0.42

my

0.41

0.40

Activations Density 0.648%

characters or symbols within the text

Code-related special characters

`@covers` or `thereof`

No Comments

No Known Activations