INDEX

Explanations

references to support and its various applications or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Fleming

-0.79

JDK

-0.74

ريبة

-0.71

Hg

-0.67

aknya

-0.64

 Vegas

-0.63

 ModelExpression

-0.63

Jes

-0.63

omitempty

-0.61

GORITH

-0.61

POSITIVE LOGITS

 support

2.00

 Support

1.84

Support

1.81

support

1.79

 supports

1.75

 SUPPORT

1.65

 Supports

1.64

 suppor

1.57

SUPPORT

1.55

supports

1.51

Activations Density 0.074%

references to support and its various applications or contexts

No Comments

No Known Activations