INDEX

Explanations

references to programming languages or related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

InjectAttribute

-0.57

 mergeFrom

-0.57

 Roskov

-0.54

лтамалар

-0.54

 gynhyrchwyd

-0.52

 censiti

-0.52

ItemLayout

-0.52

 AssemblyCulture

-0.51

hyrchwyd

-0.51

IUrlHelper

-0.50

POSITIVE LOGITS

ters

0.91

 Python

0.76

Python

0.67

tering

0.66

Py

0.65

Py

0.64

 PYTHON

0.63

 python

0.62

 packet

0.61

 capsule

0.61

Activations Density 0.314%

references to programming languages or related terminology

No Comments

No Known Activations