INDEX

Explanations

expressions related to tensor operations and dimensions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

tě

-0.45

 vorkommen

-0.45

 lema

-0.45

 décal

-0.45

ppy

-0.45

Dij

-0.43

 automatiques

-0.43

 corpi

-0.42

erton

-0.42

koch

-0.42

POSITIVE LOGITS

IntoConstraints

0.95

 AssemblyCulture

0.87

 disambiguazione

0.84

expandindo

0.82

MigrationBuilder

0.77

 numberOfRows

0.76

AddHtmlAttribute

0.76

PreferredItem

0.76

webElement

0.75

SharedCtor

0.75

Activations Density 0.178%

expressions related to tensor operations and dimensions

No Comments

No Known Activations