INDEX

Explanations

inquiries related to understanding or clarifying information

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ๆ

-0.50

SP

-0.44

yth

-0.44

兮

-0.43

Val

-0.43

 Westen

-0.43

FF

-0.42

ly

-0.42

POSITIVE LOGITS

how

1.61

 whether

1.46

how

1.21

whether

1.21

 WHETHER

1.16

DockStyle

1.12

 cómo

1.11

why

1.09

 bagaimana

1.06

 AssemblyCulture

1.04

Activations Density 0.393%

inquiries related to understanding or clarifying information

No Comments

No Known Activations