INDEX

Explanations

elements related to literary terms and definitions in a document

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

German or Norwegian words

np_acts-logits-general · gemini-2.0-flash

consecutive verbs or specific compound nouns

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

 propOrder

-0.84

ensuche

-0.77

gården

-0.73

ercises

-0.69

anhänger

-0.69

adeloupe

-0.69

veien

-0.68

spreis

-0.67

anzeige

-0.66

styrelsen

-0.66

POSITIVE LOGITS

 Diſ

0.64

var

0.60

 ſche

0.59

 Inſ

0.58

 Reſ

0.56

0.53

por

0.53

st

0.53

 aſſ

0.53

&_

0.52

Activations Density 0.059%

elements related to literary terms and definitions in a document

German or Norwegian words

consecutive verbs or specific compound nouns

No Comments

No Known Activations