INDEX

Explanations

references to detailed information or specifics in a document

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

ceptor

-0.68

GridColumn

-0.67

cabulary

-0.60

 invokevirtual

-0.58

ագրություններ

-0.58

 الدولي

-0.58

AndEndTag

-0.57

WebServlet

-0.57

Externé

-0.56

 елның

-0.56

POSITIVE LOGITS

 details

0.69

led

0.67

 Details

0.66

lierte

0.64

bred

0.64

 Exactos

0.63

={({

0.62

KURZBESCHREIBUNG

0.60

 DETAILS

0.60

 AspNetCore

0.59

Activations Density 0.099%

references to detailed information or specifics in a document

No Comments

No Known Activations