INDEX

Explanations

connections and relationships between different concepts or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

)))));

-0.68

 mxArray

-0.59

eafter

-0.55

sipasi

-0.54

Pratique

-0.54

 staked

-0.54

alf

-0.53

 forState

-0.53

visation

-0.53

 officielles

-0.52

POSITIVE LOGITS

 common

0.89

共通

0.88

common

0.74

 shared

0.73

 ortak

0.69

 gemeinsame

0.66

 together

0.66

 común

0.64

 comunes

0.63

 gemeinsamen

0.62

Activations Density 0.528%

connections and relationships between different concepts or entities

No Comments

No Known Activations