INDEX

Explanations

brackets, parentheses, and mathematical notation

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

 AssemblyTitle

-1.08

Према

-0.96

tonode

-0.94

 ModelRenderer

-0.93

 betweenstory

-0.89

NewUrlParser

-0.88

KommentareTeilen

-0.86

 HttpNotFound

-0.86

saraba

-0.86

tableFuture

-0.86

POSITIVE LOGITS

mtable

0.61

":[{

0.55

0.53

 voici

0.53

0.51

↵↵↵

0.51

0.50

HtmlAttribute

0.49

By

0.48

kr

0.48

Activations Density 0.094%

brackets, parentheses, and mathematical notation

No Comments

No Known Activations