INDEX

Explanations

syntax related to data structure definitions and message encoding in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 CreateTagHelper

-0.93

enumi

-0.92

RectangleBorder

-0.74

owol

-0.62

Efq

-0.61

ViewFeatures

-0.61

CloseOperation

-0.58

 Hopf

-0.58

 Theſe

-0.57

 AssemblyCulture

-0.57

POSITIVE LOGITS

GEBURTSDATUM

0.95

:✨

0.71

FieldNumber

0.63

//

0.61

ksessa

0.60

 <<<<<<<<<<<<<<

0.56

össä

0.55

iforn

0.55

 createSlice

0.55

 resourceCulture

0.55

Activations Density 0.064%

syntax related to data structure definitions and message encoding in a programming context

No Comments

No Known Activations