INDEX

Explanations

references to individuals or entities involved in legal or formal contexts

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

al

-0.81

 Emilia

-0.74

</b>

-0.73

}))

-0.69

 Rosenthal

-0.69

<b>

-0.69

pr

-0.69

安娜

-0.68

aal

-0.68

 Chandler

-0.66

POSITIVE LOGITS

antMatchers

1.02

 Roskov

0.98

 kappa

0.89

XmlEnum

0.87

 Dhar

0.86

Och

0.82

ocracy

0.81

 thither

0.81

 Nestor

0.80

 Esther

0.80

Activations Density 2.427%

references to individuals or entities involved in legal or formal contexts

No Comments

No Known Activations