INDEX

Explanations

terms and phrases related to qualifications and the act of qualifying

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

meeting criteria for

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

−

-0.42

bs

-0.42

-0.41

cm

-0.40

esch

-0.40

-0.39

at

-0.39

 ThemeData

-0.39

 Henson

-0.38

<h2>

-0.38

POSITIVE LOGITS

 Qualification

1.13

 qualification

1.13

 Qual

1.07

 Qualifying

1.05

 qualify

1.05

 qualifications

1.04

Qualified

1.03

 Qualifier

1.03

 qualifying

1.01

Qualification

1.01

Activations Density 0.006%

terms and phrases related to qualifications and the act of qualifying

meeting criteria for

No Comments

No Known Activations