INDEX

Explanations

exponential and polynomial notations, particularly in mathematical expressions

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

 cố

-0.55

 kecamatan

-0.54

 Meksiku

-0.53

شة

-0.51

 Mourning

-0.48

 brug

-0.48

 отделение

-0.47

 Bingham

-0.46

 ordinal

-0.46

 Deum

-0.46

POSITIVE LOGITS

+#+#

0.69

useNewUrlParser

0.65

 adev

0.60

styleType

0.59

CompilerServices

0.58

 pathlib

0.58

NameInMap

0.58

 linkovi

0.58

 RouterModule

0.58

KURZBESCHREIBUNG

0.58

Activations Density 0.584%

exponential and polynomial notations, particularly in mathematical expressions

No Comments

No Known Activations