INDEX

Explanations

references to "ends" or final parts of items or sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

onActivityResult

-0.63

 centrifugal

-0.62

iteur

-0.56

 paralysis

-0.54

ั่ง

-0.54

 trompe

-0.52

googleapis

-0.50

itrile

-0.50

oiseau

-0.50

 transients

-0.50

POSITIVE LOGITS

end

0.92

RenderAtEndOf

0.79

 estimés

0.72

PathVariable

0.69

 ends

0.65

gensen

0.63

RegressionTest

0.61

 valued

0.60

Eksterne

0.58

orianCalendar

0.58

Activations Density 0.183%

references to "ends" or final parts of items or sequences

No Comments

No Known Activations