INDEX

Explanations

whitespace characters or spaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

 sánchez

-0.85

 iſt

-0.78

 faſt

-0.75

########.

-0.73

 Monfieur

-0.72

 Anſ

-0.71

 pegat

-0.71

 ſever

-0.70

 viſ

-0.70

 合集

-0.70

POSITIVE LOGITS

↵

0.86

↵↵

0.81

0.73

</blockquote>

0.73

</em>

0.73

</h3>

0.71

</code>

0.67

</h4>

0.63

</strong>

0.60

 gyrus

0.60

Activations Density 0.001%

whitespace characters or spaces

No Comments

No Known Activations