INDEX

Explanations

elements that resemble syntax or structure typically found in programming or data coding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Parcelize

-0.70

참고

-0.70

Spoljašnje

-0.67

localctx

-0.64

NgModule

-0.64

 ویکی‌پدیا

-0.63

 estekak

-0.63

SBATCH

-0.59

UnsafeEnabled

-0.59

InstanceState

-0.58

POSITIVE LOGITS

PerformLayout

0.58

 Char

0.48

RegressionTest

0.45

 tales

0.45

صیلات

0.44

 char

0.41

he

0.40

isRequired

0.40

 AspNetCore

0.38

 مكتب

0.37

Activations Density 0.620%

elements that resemble syntax or structure typically found in programming or data coding

No Comments

No Known Activations