INDEX

Explanations

terms related to restrictions and prohibitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

fjspx

-0.76

 AssemblyVersion

-0.67

WithFormat

-0.64

IVIDUAL

-0.62

skjaer

-0.62

ghty

-0.62

ukunft

-0.60

TypedDataSet

-0.60

 GENERATED

-0.59

 بيها

-0.58

POSITIVE LOGITS

 Allowed

1.03

 allowed

1.00

 permitted

0.97

 ALLOWED

0.96

allowed

0.89

 allowable

0.87

permitted

0.87

Allowed

0.85

 tolerated

0.83

允许

0.83

Activations Density 0.299%

terms related to restrictions and prohibitions

No Comments

No Known Activations