INDEX

Explanations

references to plugins in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

NOPQRST

-0.59

はじめに

-0.54

gwt

-0.52

 CreateTagHelper

-0.51

Kre

-0.51

cal

-0.50

tagHelperRunner

-0.50

 spat

-0.50

rugada

-0.48

 quanto

-0.48

POSITIVE LOGITS

enumii

1.08

enumi

1.01

 Programming

0.96

 plugs

0.95

 programming

0.94

 Cultural

0.92

 programmers

0.82

Programming

0.82

Coded

0.80

Coding

0.78

Activations Density 0.089%

references to plugins in various contexts

No Comments

No Known Activations