INDEX

Explanations

numerals and punctuation marks that signify data or statistical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Хьажоргаш

-0.88

MigrationBuilder

-0.76

EndGlobalSection

-0.69

Autoritní

-0.68

tagHelperRunner

-0.67

RuleContext

-0.65

 بيها

-0.64

 فريبيس

-0.64

aarrggbb

-0.64

InjectAttribute

-0.62

POSITIVE LOGITS

 thousand

0.72

Thousand

0.59

thousand

0.57

一千

0.54

 Thousand

0.54

+#+#

0.52

 millennium

0.50

千

0.49

 THOUS

0.49

 tausend

0.48

Activations Density 0.582%

numerals and punctuation marks that signify data or statistical information

No Comments

No Known Activations