INDEX

Explanations

phrases indicating a change in social or political dynamics

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

state of being

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

rungsseite

-0.69

 snippetHide

-0.59

 שוליים

-0.57

principalTable

-0.53

StoryboardSegue

-0.52

PageModule

-0.51

XmlAccessorType

-0.50

 useAppContext

-0.49

tagext

-0.48

WriteAttribute

-0.48

POSITIVE LOGITS

ährend

0.35

 abnormal

0.34

ioutil

0.33

#+#

0.33

dem

0.32

Dem

0.32

Professor

0.31

 čin

0.31

ErrorResponse

0.30

 Grenzen

0.29

Activations Density 0.036%

phrases indicating a change in social or political dynamics

state of being

No Comments

No Known Activations