INDEX

Explanations

elements related to class and function definitions in Python code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

string

-0.41

ætter

-0.41

 automatiques

-0.41

 tepat

-0.41

“

-0.40

 string

-0.40

ђа

-0.37

řit

-0.37

POSITIVE LOGITS

 виправивши

1.32

basicConfig

1.05

GEBURTSDATUM

1.01

Chham

1.01

المشاركات

0.95

 Roskov

0.94

 NSCoder

0.90

UnusedPrivate

0.90

AccessorTable

0.89

ftagPool

0.87

Activations Density 0.139%

elements related to class and function definitions in Python code

No Comments

No Known Activations