INDEX

Explanations

common words and phrases typically associated with conversations or narratives

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

events and communities

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

Negative Logits

Bibliograf

-0.41

]>=

-0.40

 Audiodateien

-0.40

aronder

-0.36

ことにしました

-0.36

 wiem

-0.36

erintah

-0.36

Tikang

-0.36

Rüyada

-0.36

UnusedPrivate

-0.36

POSITIVE LOGITS

MLLoader

0.54

aarrggbb

0.52

setContentType

0.45

 Expo

0.45

ILT

0.43

 EXPO

0.43

grain

0.43

 חיצוניים

0.42

EDC

0.41

stylers

0.41

Activations Density 0.016%

common words and phrases typically associated with conversations or narratives

events and communities

No Known Activations