INDEX

Explanations

references to packaging or service packages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

CWE

-0.81

getWriter

-0.71

Ist

-0.70

JST

-0.69

 MotionEvent

-0.67

īm

-0.67

 Ehren

-0.67

EHR

-0.66

Yer

-0.65

Yer

-0.64

POSITIVE LOGITS

 package

2.32

 packages

2.15

 Package

2.10

 Packages

1.91

 PACKAGE

1.91

Package

1.89

package

1.87

PACKAGE

1.82

packages

1.81

Packages

1.70

Activations Density 0.049%

references to packaging or service packages

No Comments

No Known Activations