INDEX

Explanations

technical jargon or specialized terms within complex documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Administration

-0.53

 administration

-0.52

voi

-0.51

ptonshire

-0.45

voi

-0.45

DataAnnotations

-0.45

ocrine

-0.45

anah

-0.44

:+:

-0.44

 IEnumerable

-0.44

POSITIVE LOGITS

FieldBuilder

0.95

OrBuilder

0.94

الحياه

0.88

 autorytatywna

0.84

bitField

0.74

WithIOException

0.73

adpleegd

0.72

ειτουργ

0.71

 Builder

0.68

 Jefus

0.66

Activations Density 0.060%

technical jargon or specialized terms within complex documents

No Comments

No Known Activations