INDEX

Explanations

words related to scientific articles and politically charged events

oai_token-act-pair · gemini-2.0-flash

changes, interruptions

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

\{\\

-0.58

ResumeLayout

-0.53

(!__

-0.51

cstdio

-0.47

CWE

-0.45

 intptr

-0.45

addCriterion

-0.44

 unknownFields

-0.43

yas

-0.42

RTEE

-0.40

POSITIVE LOGITS

<bos>

0.69

Kariera

0.62

erals

0.61

celotti

0.59

cyklopedia

0.58

 insuffisamment

0.57

cheidet

0.56

ільки

0.55

WebVitals

0.54

فه

0.53

Activations Density 4.643%

words related to scientific articles and politically charged events

changes, interruptions

No Comments

No Known Activations