INDEX

Explanations

references to individuals' names and their associated actions or observations

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

Attribution of quotes

np_acts-logits-general · gemini-2.0-flash

person speaking or writing

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

Personensuche

-0.77

✨:

-0.77

 насељу

-0.70

 AssemblyCompany

-0.65

 Administrativna

-0.64

 remercier

-0.63

 fallu

-0.61

 noemen

-0.60

CreateMap

-0.59

 spreken

-0.58

POSITIVE LOGITS

 wrote

0.67

 declared

0.63

 told

0.59

 testified

0.59

 observed

0.58

 concluded

0.57

 explained

0.56

 contended

0.56

 declarado

0.54

RegressionTest

0.54

Activations Density 0.074%

references to individuals' names and their associated actions or observations

Attribution of quotes

person speaking or writing

No Comments

No Known Activations