INDEX

Explanations

names of specific organizations, projects, or publications

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

[*]

-0.69

 onCreateView

-0.48

 established

-0.46

 iscri

-0.46

Descriere

-0.44

probieren

-0.44

 llorar

-0.43

 such

-0.43

 akka

-0.43

ทร

-0.42

POSITIVE LOGITS

ſelf

0.76

 Jefus

0.68

IntoConstraints

0.62

 ducati

0.60

 Houſe

0.60

ſelves

0.59

 nuoc

0.59

 referenties

0.58

adaptiveStyles

0.58

 Chrift

0.58

Activations Density 0.266%

names of specific organizations, projects, or publications

No Comments

No Known Activations