INDEX

Explanations

instances of mathematical notation and terminology related to coding and information theory

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

aarrggbb

-0.75

SharedDtor

-0.74

DockStyle

-0.71

AsUp

-0.60

CEM

-0.58

+--

-0.58

--.

-0.58

 Fontaine

-0.56

SNS

-0.56

cozy

-0.56

POSITIVE LOGITS

text

1.51

TEXT

1.02

 text

1.01

Text

0.97

 referrerpolicy

0.92

 Text

0.88

 textStatus

0.87

TextChanged

0.87

 TEXT

0.86

 textual

0.83

Activations Density 0.056%

instances of mathematical notation and terminology related to coding and information theory

No Comments

No Known Activations