INDEX

Explanations

words related to fields of work or study

oai_token-act-pair · gemini-2.0-flash

industries

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 fotografico

-0.64

 dedans

-0.61

 espirituales

-0.60

 elettron

-0.59

 tecido

-0.58

istoitu

-0.57

 malattia

-0.57

Plane

-0.57

APORE

-0.57

 Jérusalem

-0.56

POSITIVE LOGITS

}{*}{}

0.59

verwijspagina

0.57

Viitteet

0.55

initComponents

0.50

Parcelize

0.49

Personendaten

0.47

}{*}{

0.47

lably

0.46

**********/

0.45

umberland

0.45

Activations Density 3.057%

words related to fields of work or study

industries

No Comments

No Known Activations