INDEX

Explanations

references to employment, jobs, and work-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 intptr

-0.42



-0.40

ValueStyle

-0.38

醐

-0.38

 crack

-0.38

<%@

-0.35

 MainAxisSize

-0.35

Autoritní

-0.35

 VIDEOTAPE

-0.35

VersionUID

-0.35

POSITIVE LOGITS

employment

1.00

Employment

0.99

 Employment

0.98

 employment

0.97

 laborales

0.84

 laboral

0.84

 emprego

0.80

 EMPLOYMENT

0.79

Work

0.77

mployment

0.75

Activations Density 0.364%

references to employment, jobs, and work-related concepts

No Comments

No Known Activations