INDEX

Explanations

references to formulas, theorems, and structural components in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

WebVitals

-0.68

['$

-0.61

="{{$

-0.57

::_('

-0.55

 Telling

-0.55

="{{

-0.55

%");

-0.54

 Riverside

-0.54

oa̍t

-0.54

indor

-0.53

POSITIVE LOGITS

RenderAtEndOf

0.53

 paziente

0.51

 bậc

0.50

velocityX

0.48

mobileqq

0.48

 تضيفلها

0.47

lankton

0.46

conhe

0.45

 CreateTagHelper

0.45

 ErrIntOverflow

0.44

Activations Density 0.699%

references to formulas, theorems, and structural components in a technical context

No Comments

No Known Activations