INDEX

Explanations

references to legal terminology and related entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 wireType

-0.64

 île

-0.62

 généraux

-0.58

 itſelf

-0.57

 admiten

-0.57

 pagare

-0.55

kháu

-0.55

 Bär

-0.54

 rând

-0.54

例句

-0.53

POSITIVE LOGITS

tagHelperRunner

0.85

MessageOf

0.80

DoubleQuotes

0.62

 bosh

0.62

 rail

0.57

SharedCtor

0.56

AddTagHelper

0.56

rail

0.56

Pew

0.56

 RAIL

0.55

Activations Density 0.791%

references to legal terminology and related entities

No Comments

No Known Activations