INDEX

Explanations

punctuation and formatting symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Còn

-0.59

mặt

-0.53

no

-0.51

 land

-0.50

can

-0.49

học

-0.49

aggiare

-0.47

 turn

-0.46

conce

-0.46

por

-0.46

POSITIVE LOGITS

principalColumn

0.91

IUrlHelper

0.85

/*

0.85

 насељу

0.83

TypedDataSet

0.80

//

0.77

OGND

0.75

+#+#

0.74

 beginnetje

0.74

+:+

0.72

Activations Density 0.076%

punctuation and formatting symbols

No Comments

No Known Activations