INDEX

Explanations

references to roles, functions, and responsibilities in a professional context

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

[Word] side

np_acts-logits-general · gemini-2.0-flash

side / sides / lado

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/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.24.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

 snippetHide

-0.71

 betweenstory

-0.64

ConstraintMaker

-0.59

writeFieldEnd

-0.59

Personensuche

-0.55

addGap

-0.54

المكان

-0.54

 الرياضيه

-0.54

évaluateur

-0.53

 CURIAM

-0.52

POSITIVE LOGITS

 side

4.42

 Side

3.64

side

3.61

Side

3.59

 SIDE

3.46

 sides

3.32

SIDE

3.09

sides

2.67

 Sides

2.58

 lado

2.56

Activations Density 0.523%

references to roles, functions, and responsibilities in a professional context

[Word] side

side / sides / lado

No Comments

No Known Activations