INDEX

Explanations

phrases that introduce or emphasize information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

SharedDtor

-0.58

 ogóle

-0.55

MLLoader

-0.53

 verbatim

-0.51

 dlaczego

-0.50

 bienven

-0.50

 része

-0.50

 kenapa

-0.49

 Lindberg

-0.49

LayoutConstraint

-0.49

POSITIVE LOGITS

 With

0.98

With

0.94

有了

0.79

ostante

0.78

WITH

0.69

 ligiloj

0.68

 Avec

0.67

 knowing

0.67

InputBorder

0.67

enumeration

0.65

Activations Density 0.091%

phrases that introduce or emphasize information

No Comments

No Known Activations