INDEX

Explanations

words related to identity and classification entities

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

technical and descriptive contexts

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

 push

-0.30

斯基

-0.29

uley

-0.29

 doch

-0.29

дови

-0.28

 حض

-0.28

 rollo

-0.28

 advice

-0.27

itage

-0.27

POSITIVE LOGITS

RenderAtEndOf

0.84

 surla

0.69

enumii

0.67

 autorytatywna

0.67

EDEFAULT

0.59

RTSC

0.59

 pleaſure

0.59

webElementGuid

0.59

 насељу

0.57

 ſtate

0.57

Activations Density 0.015%

words related to identity and classification entities

technical and descriptive contexts

No Comments

No Known Activations