INDEX

Explanations

information related to specific historical events and cultural contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

MigrationBuilder

-0.70

AnchorStyles

-0.66

Datuak

-0.66

getRuntime

-0.65

 defaultstate

-0.64

bitField

-0.62

ArgumentParser

-0.59

SBATCH

-0.58

dafx

-0.58

κτηρισ

-0.58

POSITIVE LOGITS

부터

0.69

 first

0.65

abord

0.58

 start

0.58

 puis

0.58

まず

0.57

 starting

0.56

 AssemblyCulture

0.56

 starters

0.55

 initial

0.55

Activations Density 0.543%

information related to specific historical events and cultural contexts

No Comments

No Known Activations