INDEX

Explanations

specific technical terms and identifiers related to programming, medical terminology, and court cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 nahilalakip

-0.86

__(/*!

-0.79

 ***!

-0.67

Παραπομπές

-0.67

 AssemblyTitle

-0.65

 >=",

-0.65

rítica

-0.64

 AssemblyCulture

-0.64

GEBURTS

-0.63

Референце

-0.61

POSITIVE LOGITS

ThroughAttribute

0.45

tamol

0.44

以外

0.44

&#

0.43

BSP

0.43

ча

0.42

plus

0.42

 değil

0.42

RegistryLite

0.41

以外の

0.41

Activations Density 1.504%

specific technical terms and identifiers related to programming, medical terminology, and court cases

No Comments

No Known Activations