INDEX

Explanations

references to a specific programming library or framework

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

MigrationBuilder

-0.77

=$?

-0.73

 itſelf

-0.68

Makefile

-0.67

redients

-0.66

Efq

-0.66

BibitemShut

-0.65

pleft

-0.65

obbies

-0.64

 ſeveral

-0.63

POSITIVE LOGITS

Kar

0.56

為了

0.56

 Papa

0.55

Pur

0.55

pur

0.54

 kasarigan

0.54

XmlType

0.53

 nuclei

0.53

autorest

0.52

Pur

0.52

Activations Density 2.596%

references to a specific programming library or framework

No Comments

No Known Activations