INDEX

Explanations

HTML tags that represent paragraphs

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

HTML paragraph tag: "<p>"

np_acts-logits-general · gemini-2.0-flash

pcre

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

handel

-0.70

en

-0.65

 kele

-0.64

engel

-0.64

fore

-0.64

)}-\

-0.63

getDatabase

-0.63

 koll

-0.62

 indic

-0.61

lla

-0.61

POSITIVE LOGITS

DispatchToProps

1.18

 pimples

1.04

ovp

1.04

1.03

SBP

0.98

 getP

0.94

Jop

0.93

Xp

0.93

kp

0.92

setP

0.91

Activations Density 0.261%

HTML tags that represent paragraphs

HTML paragraph tag: "<p>"

pcre

No Comments

No Known Activations