INDEX

Explanations

references to job-related terms and employment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 florales

-0.91

 femeninos

-0.87

 testigos

-0.85

Portail

-0.84

isateur

-0.83

 navideños

-0.82

 vectoriales

-0.81

PVA

-0.81

 Wikisource

-0.81

 artificiales

-0.80

POSITIVE LOGITS

job

1.86

Job

1.74

 Jobs

1.72

 jobs

1.71

job

1.53

JOB

1.53

Job

1.52

Jobs

1.44

JOB

1.38

jobs

1.37

Activations Density 0.034%

references to job-related terms and employment

No Comments

No Known Activations