INDEX

Explanations

phrases indicating replacement or modification relationships

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 mergeFrom

-0.53

autoconfigure

-0.53

diana

-0.52

ecken

-0.51

формление

-0.49

 misunderstood

-0.49

ggak

-0.49

 setTotal

-0.49

olia

-0.49

Delimited

-0.48

POSITIVE LOGITS

 CreateTagHelper

0.83

DockStyle

0.72

forName

0.68

GOTREF

0.61

writerow

0.61

tvguidetime

0.59

mapsto

0.59

 GenerationType

0.57

AddHtmlAttribute

0.57

 MainAxisSize

0.57

Activations Density 0.290%

phrases indicating replacement or modification relationships

No Comments

No Known Activations