INDEX

Explanations

words related to fire and explosions

oai_token-act-pair · gemini-2.0-flash

mentions of locations or places

np_token-act-pair-logits · gpt-4o-mini

locations and positions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personensuche

-0.65

 écoulé

-0.58

BASEPATH

-0.57

 BorderSide

-0.57

KommentareTeilen

-0.55

OGND

-0.54

 MotionEvent

-0.52

AIT

-0.51

fjspx

-0.51

WriteTagHelper

-0.51

POSITIVE LOGITS

the

1.04

 where

0.62

phora

0.57

ArrowToggle

0.52

where

0.48

*}\

0.47

новништво

0.47

stø

0.46

 Independencia

0.45

himovic

0.45

Activations Density 4.668%

words related to fire and explosions

mentions of locations or places

locations and positions

No Comments

No Known Activations