INDEX

Explanations

references to significant observations or findings in scientific texts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Sart

-0.48

 belong

-0.47

 communism

-0.47

ciare

-0.47

belongs

-0.45

 belonged

-0.44

vang

-0.43

 masterpiece

-0.43

Nih

-0.43

 operated

-0.42

POSITIVE LOGITS

0.81

EDEFAULT

0.78

BufferException

0.77

didSet

0.75

 nahilalakip

0.72

 ujednoznacz

0.70

oredCriteria

0.70

">//

0.69

脚注の使い方

0.69

 ImportError

0.68

Activations Density 0.329%

references to significant observations or findings in scientific texts

No Comments

No Known Activations