INDEX

Explanations

variables and parameters related to programming or mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 violence

-1.08

 voltage

-1.06

 valley

-1.01

village

-1.00

 Violence

-1.00

 village

-1.00

 valve

-0.99

volume

-0.97

Violence

-0.97

 Vice

-0.96

POSITIVE LOGITS

 beginnetje

0.53

 disambiguazione

0.53

########.

0.52

 Picchu

0.51

 surla

0.42

dańsk

0.42

RTHOOK

0.42

scrapy

0.42

BorderFactory

0.42

脚注の使い方

0.42

Activations Density 0.251%

variables and parameters related to programming or mathematical expressions

No Comments

No Known Activations