INDEX

Explanations

code-related symbols and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Pust

-0.79

CWE

-0.77

Portale

-0.77

Ruz

-0.73

etron

-0.72

bootstrapcdn

-0.71

 Lazar

-0.71

 Pinto

-0.70

 TType

-0.67

igno

-0.65

POSITIVE LOGITS

//

0.75

\{\\

0.74

[toxicity=0]

0.71

 scoperta

0.58

varlak

0.58

 capables

0.58

 tarko

0.56

 remercier

0.56

nisk

0.55

0.54

Activations Density 0.070%

code-related symbols and structure

No Comments

No Known Activations