INDEX

Explanations

terms related to ratings, measurements, or evaluations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 المعيارى

-0.94

adpleegd

-0.66

 Италијани

-0.65

jsxFileName

-0.59

 вікі

-0.59

 linkovi

-0.56

 виправивши

-0.56

 ControllerBase

-0.55

Aiheesta

-0.54

ніципалі

-0.53

POSITIVE LOGITS

WriteTagHelper

1.02

 SafeMath

0.91

ValueStyle

0.88

RegressionTest

0.67

 disponibilités

0.66

LookAnd

0.65

RetentionPolicy

0.64

 ſever

0.64

TagMode

0.62

 ſche

0.62

Activations Density 8.450%

terms related to ratings, measurements, or evaluations

No Comments

No Known Activations