INDEX

Explanations

questions or phrases seeking clarification or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

StructEnd

-0.78

 Roskov

-0.72

ImageContext

-0.69

 protoimpl

-0.68

 suivantes

-0.68

 invokingState

-0.67

InjectAttribute

-0.67

+#+#

-0.65

DeleteBehavior

-0.65

<bos>

-0.64

POSITIVE LOGITS

 kind

1.25

 type

1.13

 kinds

1.07

 sort

1.04

 types

0.95

kind

0.89

 portion

0.86

 direction

0.85

sort

0.85

 parts

0.85

Activations Density 0.135%

questions or phrases seeking clarification or information

No Comments

No Known Activations