INDEX

Explanations

mathematical and programming terminology related to calculations and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

-0.56

in

-0.55

-0.53

on

-0.52

and

-0.52

at

-0.50

 just

-0.49

 seven

-0.48

so

-0.48

<strong>

-0.46

POSITIVE LOGITS

 utafitiHapana

1.18

WebVitals

1.03

 AssemblyCulture

0.94

AndEndTag

0.93

تقاوى

0.86

ThroughAttribute

0.85

 CreateTagHelper

0.85

MethodManager

0.85

 lowa

0.84

enumi

0.82

Activations Density 0.340%

mathematical and programming terminology related to calculations and functions

No Comments

No Known Activations