INDEX

Explanations

technical terms and parameters used in scientific or programming contexts

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

again and numerical units

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

 الحره

-0.54

 BorderSide

-0.52

 unknownFields

-0.50

cillor

-0.49

delwed

-0.47

 Sulph

-0.46

IsMutable

-0.45

AnchorTagHelper

-0.44

getItemId

-0.44

cheduling

-0.43

POSITIVE LOGITS

 again

0.52

Again

0.50

 Again

0.48

again

0.47

 nữa

0.46

 wiederum

0.42

 AGAIN

0.41

又要

0.39

 nuevamente

0.39

fromnode

0.36

Activations Density 0.038%

technical terms and parameters used in scientific or programming contexts

again and numerical units

No Comments

No Known Activations