INDEX

Explanations

numeric representations and patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 useStyles

-0.56

 Tenth

-0.53

ⓧ

-0.51

oneofs

-0.49

SBATCH

-0.48

 tenth

-0.46

 لات

-0.45

 sixth

-0.45

JoinTable

-0.44

 onCancelled

-0.44

POSITIVE LOGITS

1.41

 Third

1.14

 Three

1.11

 three

1.05

３

1.03

 ketiga

1.02

 THREE

1.01

 trio

1.01

 third

1.00

 thirds

0.99

Activations Density 1.113%

numeric representations and patterns

No Comments

No Known Activations