INDEX

Explanations

names and identifiers related to people 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 @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Baccarat

-0.57

 becauſe

-0.56

boutin

-0.55

VersionUID

-0.55

WTA

-0.54

 fufficient

-0.53

 ſta

-0.52

**)

-0.52

 estekak

-0.51

 ISTAT

-0.50

POSITIVE LOGITS

astify

0.53

ContentAsync

0.52

MarshalTo

0.50

OrNil

0.50

 autorytatywna

0.49

BoxLayout

0.47

addCriterion

0.47

LookAnd

0.47

 jorden

0.45

 Bioaccumulative

0.45

Activations Density 0.259%

names and identifiers related to people or entities

No Comments

No Known Activations