INDEX

Explanations

instances of numbers and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

-0.52

+#+

-0.39

fromnode

-0.38

 grain

-0.38

 labor

-0.38

pen

-0.37

lat

-0.36

etine

-0.35

makeText

-0.35

 liberty

-0.35

POSITIVE LOGITS

 propOrder

0.58

 pitä

0.57

 mukana

0.55

 HttpNotFound

0.54

 tirantes

0.54

 typelib

0.54

 Comprometido

0.54

utilisons

0.53

 olisi

0.52

openzeppelin

0.52

Activations Density 0.337%

instances of numbers and related terms

No Comments

No Known Activations