INDEX

Explanations

details about interaction processes and workflows

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

 Aziz

-0.42

paksa

-0.40

næ

-0.39

nima

-0.38

σεων

-0.37

 syarat

-0.37

ситет

-0.37

utsche

-0.37

gyű

-0.37

glTex

-0.37

POSITIVE LOGITS

脚注の使い方

0.90

tagHelperRunner

0.85

findpost

0.72

 disambiguazione

0.72

 yourselves

0.71

帖最后由

0.71

 doInBackground

0.70

发表于

0.70

ArgsConstructor

0.69

SharedDtor

0.69

Activations Density 0.363%

details about interaction processes and workflows

No Comments

No Known Activations