INDEX

Explanations

references to users and policies in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

RegressionTest

-0.67

$_"

-0.55

صابة

-0.52

 barbati

-0.50

WaitGroup

-0.50

 Monfieur

-0.49

 getArguments

-0.49

 beſt

-0.48

 fossa

-0.48

—

-0.48

POSITIVE LOGITS

 oprot

0.72

 transfieras

0.61

JspWriter

0.61

GEBURTSDATUM

0.60

 سكانية

0.60

 propOrder

0.60

 mergeFrom

0.56

featureID

0.55

 Мексичка

0.55

$_['

0.52

Activations Density 0.441%

references to users and policies in technical contexts

No Comments

No Known Activations