INDEX

Explanations

terms related to work and employment contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

paravant

-1.01

quelize

-1.00

zbęd

-0.93

 Enfield

-0.86

CTP

-0.82

Datuak

-0.80

 GIPHY

-0.80

Ведь

-0.79

 desconhe

-0.79

 Aerosol

-0.78

POSITIVE LOGITS

 work

1.55

 works

1.46

Work

1.43

 WORK

1.42

 Work

1.42

work

1.40

WORK

1.33

 Works

1.28

Works

1.26

works

1.25

Activations Density 0.096%

terms related to work and employment contexts

No Comments

No Known Activations