INDEX

Explanations

terms related to medical measurements and assessments

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

Followed by punctuation (, . ? -) and some other tokens

np_acts-logits-general · gemini-2.0-flash

influence to, Go to, one is

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

MigrationBuilder

-0.74

__':

-0.72

 Comprometido

-0.69

 дописавши

-0.68

 Alexey

-0.67

astéro

-0.67

 ARXIV

-0.66

\{\\

-0.66

FTFY

-0.65

+)/

-0.65

POSITIVE LOGITS

 also

0.58

0.56

 most

0.55

Bardzo

0.54

0.53

 connaît

0.53

Mrs

0.52

TargetException

0.52

 самы

0.50

of

0.50

Activations Density 0.083%

terms related to medical measurements and assessments

Followed by punctuation (, . ? -) and some other tokens

influence to, Go to, one is

No Comments

No Known Activations