INDEX

Explanations

various punctuation marks and spacing tokens in the text

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

Code snippets, especially regions and offsets

np_acts-logits-general · gemini-2.0-flash

hexadecimal numbers and code snippets

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

 Jefus

-0.99

PerformLayout

-0.91

évaluateur

-0.86

AndEndTag

-0.86

 itſelf

-0.84

 }}$}

-0.81

 ſhe

-0.81

 purpoſe

-0.80

]")]

-0.78

ſelves

-0.78

POSITIVE LOGITS

AutoField

0.61

 kasarigan

0.57

statechange

0.44

 acceptez

0.44

gu

0.44

ICULO

0.42

Datuak

0.42

Dış

0.42

ugna

0.42

Top

0.41

Activations Density 0.257%

various punctuation marks and spacing tokens in the text

Code snippets, especially regions and offsets

hexadecimal numbers and code snippets

No Comments

No Known Activations