INDEX

Explanations

code snippets related to programming functions and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

éry

-0.48

jois

-0.47

Framebuffer

-0.46

 Helf

-0.46

INGHAM

-0.46

 useEffect

-0.45

bando

-0.44

 rimb

-0.43

λια

-0.43

 Evidence

-0.43

POSITIVE LOGITS

ValueStyle

0.80

 esternos

0.74

 BoxFit

0.71

AndEndTag

0.70

 estekak

0.70

 ModelExpression

0.69

sizeCache

0.68

MessageOf

0.67

EDEFAULT

0.67

XmlEnum

0.67

Activations Density 0.138%

code snippets related to programming functions and parameters

No Comments

No Known Activations