INDEX

Explanations

numerical and date values associated with events or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LookAnd

-0.72

IBAction

-0.53

WriteAttribute

-0.53

 CanadaChoose

-0.49

Vidite

-0.48

RAINT

-0.47

 ویکی

-0.47

igshid

-0.46

Chham

-0.46

lccn

-0.46

POSITIVE LOGITS

DoubleQuotes

0.69

msgTypes

0.65

0.58

\{\\

0.55

unnitel

0.54

%");

0.54

()]);

0.54

 NgModule

0.53

 Ambiental

0.53

tshell

0.52

Activations Density 0.052%

numerical and date values associated with events or entities

No Comments

No Known Activations