INDEX

Explanations

terms related to protection and proteins

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 HasFactory

-0.90

 فريبيس

-0.86

 PLWABN

-0.84

 Cassini

-0.75

 للاسماء

-0.73

 CommonModule

-0.68

RegressionTest

-0.65

 toppers

-0.64

Gim

-0.64

 Auger

-0.62

POSITIVE LOGITS

 against

0.86

 protects

0.71

 shield

0.70

 Against

0.68

 Protects

0.66

against

0.66

 contre

0.65

 Protect

0.64

 protect

0.64

guarded

0.63

Activations Density 0.159%

terms related to protection and proteins

No Comments

No Known Activations