INDEX

Explanations

technical terms and identifiers related to scientific or engineering contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Wikimedijinoj

-1.08

IntoConstraints

-1.04

AntiForgeryToken

-0.87

">//

-0.85

 doInBackground

-0.79

Personendaten

-0.77

脚注の使い方

-0.75

 EconPapers

-0.75

ContentLoaded

-0.72

 Chwiliwch

-0.72

POSITIVE LOGITS

 appelez

0.45

 بخوانید

0.44

tagHelperRunner

0.42

 potencial

0.42

Kind

0.42

锈钢

0.41

poss

0.40

 colspan

0.40

大根

0.39

ya

0.39

Activations Density 6.416%

technical terms and identifiers related to scientific or engineering contexts

No Comments

No Known Activations