INDEX

Explanations

references to professional careers and career-related achievements

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

career context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<h1>

-0.45

 Sotto

-0.44

 North

-0.43

Nix

-0.43

 White

-0.41

 South

-0.41

 Willow

-0.40

 Middleton

-0.39

 Noord

-0.39

Ash

-0.39

POSITIVE LOGITS

career

1.07

 career

1.07

Career

1.04

 Career

0.96

Carreira

0.93

 CAREER

0.87

CAREER

0.85

 carreira

0.84

 careers

0.81

Careers

0.81

Activations Density 0.006%

references to professional careers and career-related achievements

career context

No Comments

No Known Activations