INDEX

Explanations

references to levels in a hierarchical or structured context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NameInMap

-0.89

şiv

-0.66

 utafitiHapana

-0.64

 ModelExpression

-0.64

()");

-0.61

>",

-0.60

()")

-0.59

httphttps

-0.59

};*/

-0.59

.");

-0.58

POSITIVE LOGITS

 level

0.92

 úrov

0.67

level

0.67

 niveau

0.65

 уровня

0.63

 LEVEL

0.63

レベル

0.60

 Level

0.59

nivå

0.59

 уровне

0.59

Activations Density 0.327%

references to levels in a hierarchical or structured context

No Comments

No Known Activations