INDEX

Explanations

numerical references or citations, particularly in academic contexts

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

 Conseils

-0.48

Old

-0.48

 vecchio

-0.47

old

-0.47

ΡΙ

-0.44

遍

-0.44

 impressão

-0.43

 mümkün

-0.43

 AssemblyVersion

-0.43

 best

-0.42

POSITIVE LOGITS

脚注の使い方

1.02

 autorytatywna

0.86

 kasarigan

0.86

 مرئيه

0.77

AddTagHelper

0.76

 propOrder

0.76

MigrationBuilder

0.72

LabelTagHelper

0.72

<bos>

0.71

 Roskov

0.70

Activations Density 0.195%

numerical references or citations, particularly in academic contexts

No Comments

No Known Activations