INDEX

Explanations

words related to characters involved in an ongoing conflict

oai_token-act-pair · gemini-2.0-flash

superpowers/battles

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

<()>

-0.68

Tikang

-0.68

Билгалдахарш

-0.53

Tag

-0.52

 plong

-0.51

 phí

-0.51

thâu

-0.50

mtrl

-0.50

Tag

-0.50

tag

-0.50

POSITIVE LOGITS

ModelSerializer

0.59

IsContent

0.51

DockStyle

0.50

commons

0.49

agrad

0.48

asilkan

0.47

 Staple

0.47

butuhkan

0.46

stages

0.45

 Arxivat

0.44

Activations Density 2.476%

words related to characters involved in an ongoing conflict

superpowers/battles

No Comments

No Known Activations