INDEX

Explanations

references to theft or missing items and security measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

ArgsConstructor

-0.61

MLLoader

-0.58

tagext

-0.56

 ModelExpression

-0.56

tonode

-0.55

 препратки

-0.54

/*

-0.52

TSCA

-0.52

hability

-0.52

AutoScale

-0.51

POSITIVE LOGITS

 security

0.97

security

0.79

 securely

0.79

 Security

0.78

 secure

0.77

Security

0.76

 Secure

0.72

 theft

0.70

secure

0.69

Secure

0.68

Activations Density 0.424%

references to theft or missing items and security measures

No Comments

No Known Activations