INDEX

Explanations

events or significant changes happening in a narrative context

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

events that happen

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 pleaſure

-0.50

dets

-0.49

 dets

-0.49

 itſelf

-0.47

AISSEE

-0.46

 EXACT

-0.44

erat

-0.42

 Detector

-0.41

wami

-0.41

一日

-0.41

POSITIVE LOGITS

теризу

0.47

onViewCreated

0.47

ponses

0.46

VersionUID

0.45

 collide

0.42

onAttach

0.42

AutoField

0.42

getMinutes

0.41

collide

0.41

 provas

0.40

Activations Density 0.026%

events or significant changes happening in a narrative context

events that happen

No Comments

No Known Activations