INDEX

Explanations

code snippets defining classes and their properties in programming languages

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

revert

-0.54

arraycopy

-0.51

indung

-0.46

ctical

-0.45

 مرئيه

-0.45

atuor

-0.42

באנגלית

-0.42

ectos

-0.41

leby

-0.41

SBATCH

-0.41

POSITIVE LOGITS

DockStyle

0.81

IntoConstraints

0.68

pulumi

0.67

AndEndTag

0.66

 unknownFields

0.59

FilterChain

0.57

WebpackPlugin

0.56

 <<<<<<<<<<<<<<

0.55

{?>

0.54

NameInMap

0.54

Activations Density 0.474%

code snippets defining classes and their properties in programming languages

No Comments

No Known Activations