INDEX

Explanations

special characters or formatting symbols, particularly related to encoding issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

SequentialGroup

-0.72

 poros

-0.68

DOS

-0.66

 forn

-0.66

》.

-0.65

 pary

-0.65

 المعيارى

-0.63

owy

-0.62

📌

-0.62

RegressionTest

-0.62

POSITIVE LOGITS

â

1.29

â

1.14

lâ

0.99

Mâ

0.99

Câ

0.98

'&#

0.98

sâ

0.90

câ

0.89

Bâ

0.89

vâ

0.86

Activations Density 0.205%

special characters or formatting symbols, particularly related to encoding issues

No Comments

No Known Activations