INDEX

Explanations

discussions about employment and work-related experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 crack

-0.37

 control

-0.36

 Bestand

-0.33

 Ausstattung

-0.32

 Twain

-0.31

 hivyo

-0.31

 cost

-0.30

 Materiales

-0.30

jangkau

-0.30

 touch

-0.30

POSITIVE LOGITS

 employment

0.91

employment

0.91

Employment

0.82

 jobs

0.79

 Employment

0.79

 unemployment

0.75

EMPLOYMENT

0.73

 occupational

0.71

job

0.71

jobs

0.70

Activations Density 0.331%

discussions about employment and work-related experiences

No Comments

No Known Activations