INDEX

Explanations

references to research studies and their corresponding identifiers or metadata

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 tartalomajánló

-0.84

SharedDtor

-0.69

ContentAlignment

-0.68

zono

-0.62

IUrlHelper

-0.57

bulos

-0.56

 présidenti

-0.56

 Tirol

-0.55

adpleegd

-0.55

 Turb

-0.55

POSITIVE LOGITS

CloseOperation

0.74

 okhttp

0.65

nonatomic

0.62

RectangleBorder

0.62

 IBOutlet

0.61

بوابة

0.58

 nonatomic

0.58

 SPDX

0.57

 cref

0.55

getRuntime

0.54

Activations Density 0.062%

references to research studies and their corresponding identifiers or metadata

No Comments

No Known Activations