INDEX

Explanations

the word "went" or "go" in association with career trajectory

oai_token-act-pair · gemini-2.0-flash

go

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

tand

-0.66

AMED

-0.65

thmetic

-0.64

 Akismet

-0.63

unately

-0.61

iffance

-0.60

colage

-0.59

^(@)

-0.58

ibatis

-0.57

ρίς

-0.57

POSITIVE LOGITS

IntoConstraints

0.60

 MessageBoxIcon

0.51

MessageState

0.50

Personensuche

0.47

RTLD

0.45

 utafitiHapana

0.44

 Италијани

0.42

ti

0.42

 vuitton

0.42

 transférez

0.41

Activations Density 0.647%

the word "went" or "go" in association with career trajectory

go

No Comments

No Known Activations