INDEX

Explanations

numerical values in varying contexts or arrangements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Appel

-0.60

jo

-0.60

Bra

-0.57

(__('

-0.56

 Weiss

-0.55

 FontWeight

-0.54

Hentet

-0.54

valle

-0.53

Tim

-0.51

RequestMapping

-0.51

POSITIVE LOGITS

↵

1.04

ViewFeatures

1.00

[toxicity=0]

0.99

</caption>

0.95

\}\\

0.94

 nakalista

0.94

 reaſon

0.93

}}$\\

0.91

uxxxx

0.91

<tbody>

0.91

Activations Density 0.144%

numerical values in varying contexts or arrangements

No Comments

No Known Activations