INDEX

Explanations

technical terms related to validation and accuracy in scientific contexts

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

sidemargin

-0.82

RegressionTest

-0.80

الإنجليزية

-0.68

 BorderRadius

-0.67

 lenker

-0.65

 <=",

-0.65

 informée

-0.64

AddHtmlAttribute

-0.62

Carriera

-0.62

tvguidetime

-0.61

POSITIVE LOGITS

oma

0.45

dzie

0.43

rien

0.42

itare

0.42

 activities

0.41

doria

0.41

GHIJKLM

0.41

πό

0.41

ISHA

0.40

鸿

0.40

Activations Density 0.722%

technical terms related to validation and accuracy in scientific contexts

No Comments

No Known Activations