INDEX

Explanations

text related to significant events or impactful actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.17.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

 […]

-0.62

Показать

-0.56

fjspx

-0.51

↵↵

-0.50

**********/

-0.48

',...

-0.47

<eos>

-0.47

otsu

-0.45

"];

-0.45

POSITIVE LOGITS

XmlAccessType

0.95

 contextLoads

0.93

 ExecuteAsync

0.93

Diwedd

0.86

endphp

0.84

enderror

0.82

出版年

0.80

انيف

0.79

 ivelany

0.74

KommentareTeilen

0.72

Activations Density 0.083%

text related to significant events or impactful actions

No Comments

No Known Activations