INDEX

Explanations

sections marked by various symbols or indices in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Unmarshaller

-0.55

oredCriteria

-0.54

elemField

-0.49

ForValue

-0.47

PreferredItem

-0.47

nestjs

-0.47

CodeAttribute

-0.47

ChromeDriver

-0.46

RepeatedField

-0.46

PullParser

-0.45

POSITIVE LOGITS

 المعيارى

0.94

 ſtate

0.88

出版年

0.87

 purpoſe

0.84

 myſelf

0.82

 Diſ

0.82

 itſelf

0.81

 Majefty

0.80

 pleaſure

0.79

 leaſt

0.79

Activations Density 0.499%

sections marked by various symbols or indices in a structured format

No Comments

No Known Activations