INDEX

Explanations

mathematical notation or symbols

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

Code or math within square brackets

np_acts-logits-general · gemini-2.0-flash

\[pr:R=Fseq\]

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

du

-0.49

es

-0.49

-0.48

führen

-0.46

up

-0.43

re

-0.43

########.

-0.41

va

-0.41

Du

-0.41

POSITIVE LOGITS

 للاسماء

1.14

 propOrder

1.00

 CommonModule

0.96

 InputDecoration

0.92

\]

0.89

reportWebVitals

0.89

 صوتيه

0.88

:✨

0.85

soever

0.82

 HasFactory

0.81

Activations Density 0.110%

mathematical notation or symbols

Code or math within square brackets

\[pr:R=Fseq\]

No Comments

No Known Activations