INDEX

Explanations

references to optional features or specifications in technological contexts

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

in languages other than English

np_acts-logits-general · gemini-2.0-flash

the following words

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

ArrowToggle

-0.91

AndEndTag

-0.87

writeFieldEnd

-0.86

 CreateTagHelper

-0.80

 Италијани

-0.80

RenderAtEndOf

-0.79

enumi

-0.72

titleMargin

-0.72

 Patro

-0.71

 שוליים

-0.71

POSITIVE LOGITS

 képes

0.59

 esetén

0.59

 készült

0.58

 különböz

0.57

 számára

0.56

 lenne

0.54

gaande

0.54

 mêmes

0.54

 varsa

0.54

 জন্য

0.54

Activations Density 0.681%

references to optional features or specifications in technological contexts

in languages other than English

the following words

No Comments

No Known Activations