INDEX

Explanations

specific terms and elements related to legal and structural definitions in arguments

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

 literario

-0.36

 fotográfico

-0.33

 gruesa

-0.31

 Untersuch

-0.28

 casero

-0.28

 altas

-0.28

 geométrico

-0.27

 enfermo

-0.27

 adecuado

-0.27

 adequado

-0.27

POSITIVE LOGITS

+#+#

0.77

 Italijanski

0.74

CppMethod

0.74

 OMITBAD

0.73



0.71

MigrationBuilder

0.71

 dAtA

0.70

rrggbb

0.69

windowFixed

0.69

elemField

0.67

Activations Density 3.556%

specific terms and elements related to legal and structural definitions in arguments

No Comments

No Known Activations