INDEX

Explanations

terms related to software implementation and project details

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

migrationBuilder

-0.78

 TextInputType

-0.76

GraphicsUnit

-0.75

InjectAttribute

-0.73

awtextra

-0.72

ContentAsync

-0.68

 '\\;'

-0.68

PerformLayout

-0.68

basicConfig

-0.67

TestingModule

-0.67

POSITIVE LOGITS

 development

0.90

 developers

0.88

开源

0.86

 developed

0.85

 project

0.84

 developer

0.77

 desenvol

0.77

 community

0.76

 개발

0.76

 GitHub

0.75

Activations Density 0.924%

terms related to software implementation and project details

No Comments

No Known Activations