INDEX

Explanations

references to medical conditions and related technical terms

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

Tokens containing "ll" or ending in "ll"

np_acts-logits-general · gemini-2.0-flash

words ending in all or ell

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Gustavo

-0.48

 Pingback

-0.48

orace

-0.47

<?

-0.46

 skriva

-0.46

athread

-0.45

suma

-0.44

Gustavo

-0.44

 McCormick

-0.44

racha

-0.43

POSITIVE LOGITS

all

0.78

alling

0.72

el

0.69

aller

0.69

ill

0.68

del

0.67

ell

0.67

ial

0.67

ail

0.66

alls

0.65

Activations Density 0.728%

references to medical conditions and related technical terms

Tokens containing "ll" or ending in "ll"

words ending in all or ell

No Comments

No Known Activations