INDEX

Explanations

programming terminology related to frameworks and data types

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 AssemblyTitle

-0.94

 Himo

-0.80

المناصب

-0.75

TagMode

-0.70

nologue

-0.67

 élevées

-0.66

 nationaux

-0.65

 nephe

-0.65

 Clipboard

-0.64

 Moderne

-0.64

POSITIVE LOGITS

int

0.74

Ӏ

0.72

IUrlHelper

0.69

typeorm

0.67

Kanpo

0.65

UALLY

0.54

UnknownFields

0.53

widgets

0.52

components

0.49

lementary

0.49

Activations Density 0.001%

programming terminology related to frameworks and data types

No Comments

No Known Activations