INDEX

Explanations

references to specific phrases or notable quotes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Jefus

-0.69

 houſe

-0.67

 currently

-0.66

 Majefty

-0.64

iuo

-0.62

Eſ

-0.61

 purpoſe

-0.61

Ideally

-0.61

 Chriſt

-0.61

 cauſe

-0.61

POSITIVE LOGITS

!...

0.69

 (…)

0.67

tonode

0.64

 MainAxisSize

0.61

__":

0.60

randrange

0.59

featureID

0.58

ArgsConstructor

0.58

 (...)

0.57

Ecotoxicity

0.56

Activations Density 0.083%

references to specific phrases or notable quotes

No Comments

No Known Activations