INDEX

Explanations

references to scientific authors and their works

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

diger

-0.44

 parall

-0.40

 acquire

-0.40

 diser

-0.40

-0.39

amo

-0.39

ấc

-0.38

aves

-0.38

-0.37

nsis

-0.37

POSITIVE LOGITS

#+#

0.92

expandindo

0.92

 AssemblyCulture

0.91

+#+

0.85

}))

0.84

 himo

0.83

 CURIAM

0.82

 تعدى

0.81

"}")

0.79

 estekak

0.75

Activations Density 0.525%

references to scientific authors and their works

No Comments

No Known Activations