INDEX

Explanations

technical terms and identifiers within scientific and programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Дереккөздер

-0.59

ktas

-0.53

 round

-0.52

elemField

-0.51

println

-0.46

Round

-0.45

OrderDetails

-0.45

 Round

-0.45

eri

-0.44

 pieds

-0.43

POSITIVE LOGITS

TagHelpers

0.91

UrlResolution

0.88

 محفوظة

0.87

RectangleBorder

0.80

+:+

0.78

 Warehouse

0.72

IntoConstraints

0.67

 haunted

0.67

 JpaRepository

0.66

 numberOfRows

0.66

Activations Density 2.039%

technical terms and identifiers within scientific and programming contexts

No Comments

No Known Activations