INDEX

Explanations

references to fraud and related terminology

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WriteTagHelper

-0.62

SerializedSize

-0.58

はじめに

-0.57

Специ

-0.54

}])

-0.54

таж

-0.54

DataInputStream

-0.53

 Maitland

-0.53

usti

-0.53

 lustre

-0.53

POSITIVE LOGITS

lip

1.04

 Drift

0.78

Drift

0.75

lip

0.71

 drift

0.69

Lip

0.62

RegistryLite

0.61

 grief

0.61

 Puerto

0.60



0.59

Activations Density 0.067%

references to fraud and related terminology

No Comments

No Known Activations