INDEX

Explanations

terms related to safety and security

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 AssemblyVersion

-0.77

reportWebVitals

-0.75

SharedDtor

-0.69

astéroïdes

-0.68

RegressionTest

-0.65

memoized

-0.64

 uVar

-0.63

="@+

-0.63

itesse

-0.63

 Autorisations

-0.62

POSITIVE LOGITS

 Safe

1.57

safe

1.57

 safe

1.50

Safe

1.49

saf

1.26

 safely

1.20

saf

1.19

 SAFE

1.18

SAFE

1.15

Saf

1.05

Activations Density 0.115%

terms related to safety and security

No Comments

No Known Activations