INDEX

Explanations

references to individual accomplishments or attributes, particularly in a sports or academic context

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

career and lifetime

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

Datuak

-0.63

jaciół

-0.45

 siyang

-0.45

exitRule

-0.44

 drapeau

-0.43

Abraço

-0.43

AndEndTag

-0.43

 AssemblyVersion

-0.43

ricane

-0.42

 desmotivaciones

-0.42

POSITIVE LOGITS

 tenure

0.76

 career

0.59

 lifetime

0.57

 lifetimes

0.50

 journey

0.48

gridx

0.48

 history

0.47

 travels

0.46

 careers

0.46

 stay

0.46

Activations Density 0.022%

references to individual accomplishments or attributes, particularly in a sports or academic context

career and lifetime

No Comments

No Known Activations