INDEX

Explanations

terms related to parameters and definitions in a scientific or mathematical 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 '/';

-0.83

 CONDU

-0.72

 '.';

-0.71

خاذ

-0.71

RLock

-0.69

 تضيفلها

-0.68

 DIOS

-0.68

 ".";

-0.68

/>";

-0.66

 onCreateView

-0.65

POSITIVE LOGITS

 parameters

1.57

 Parameters

1.49

 parameter

1.48

parameters

1.42

Parameters

1.37

setParameter

1.33

 Parameter

1.32

PARAM

1.28

 params

1.27

parameter

1.27

Activations Density 0.055%

terms related to parameters and definitions in a scientific or mathematical context

No Comments

No Known Activations