INDEX

Explanations

reported speech or references to statements made by individuals

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

reporting speech

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

-0.67

fjspx

-0.60

-------

-0.57

Numerology

-0.57

saraba

-0.57

AlterField

-0.56

LEncoder

-0.56

ſelf

-0.56

BASEPATH

-0.55

featureID

-0.54

POSITIVE LOGITS

MigrationBuilder

0.56

 compréhen

0.35

 another

0.35

ifié

0.34

why

0.34

 recent

0.33

zarchiwizowane

0.33

 reciente

0.33

 собрать

0.33

ésult

0.32

Activations Density 0.004%

reported speech or references to statements made by individuals

reporting speech

No Comments

No Known Activations