INDEX

Explanations

terms related to declarations and statements of interest or conflict

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

IContainer

-0.74

rzost

-0.73

 المعيارى

-0.65

ClientSize

-0.61

耿

-0.59

oneofs

-0.59

äksi

-0.59

zzleHttp

-0.58

 évolu

-0.57

 hueco

-0.57

POSITIVE LOGITS

 Declare

2.02

 declaration

2.02

 declare

2.01

 declared

2.00

 declaring

2.00

 declarations

1.99

 declares

1.99

declared

1.73

 Declaration

1.72

 Declarations

1.67

Activations Density 0.154%

terms related to declarations and statements of interest or conflict

No Comments

No Known Activations