INDEX

Explanations

references to complex notation or formatting in mathematical expressions

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

mathematical functions in sets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

consulté

-0.59

 templado

-0.55

richTextPanel

-0.51

pecabe

-0.47

pantalón

-0.47

 Constitucional

-0.46

SequentialGroup

-0.46

 müm

-0.46

antwoorden

-0.46

 meditación

-0.46

POSITIVE LOGITS

⟬

0.48

TokenNameLBRACE

0.46

coil

0.46

edly

0.46

 oprot

0.45

kna

0.44

kna

0.44

ed

0.43

SharedDtor

0.42

 Hein

0.41

Activations Density 0.089%

references to complex notation or formatting in mathematical expressions

mathematical functions in sets

No Comments

No Known Activations