INDEX

Explanations

references to different groups or categories of people within research studies

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

groups of people

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

<bos>

-0.37

 Fácil

-0.35

 rêves

-0.33

 graduación

-0.33

 independencia

-0.33

ConstraintMaker

-0.32

 dulces

-0.31

 dernières

-0.31

 last

-0.31

verläs

-0.31

POSITIVE LOGITS

 populations

1.12

 Populations

0.91

 population

0.85

 popolazione

0.83

populations

0.83

bootstrapcdn

0.79

 poblaciones

0.78

Populations

0.77

 Population

0.75

 população

0.73

Activations Density 0.034%

references to different groups or categories of people within research studies

groups of people

No Comments

No Known Activations