INDEX

Explanations

references to job roles and employment situations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

employment or jobs

np_acts-logits-general · gemini-2.0-flash

work and jobs

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sträger

-0.56

DoubleQuotes

-0.53

newArrayList

-0.52

LEncoder

-0.52

Viitteet

-0.51

 inför

-0.49

={`${

-0.49

 NgModule

-0.49

setVerticalGroup

-0.48

rollment

-0.48

POSITIVE LOGITS

 jobs

1.24

job

0.97

jobs

0.94

 Jobs

0.89

Jobs

0.88

job

0.84

 emprego

0.82

 employed

0.81

 employment

0.79

 working

0.79

Activations Density 0.215%

references to job roles and employment situations

employment or jobs

work and jobs

No Comments

No Known Activations