INDEX

Explanations

elements within structured data and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

jaj

-0.48

нё

-0.46

 Crosse

-0.45

JCheckBox

-0.43

hasMoreElements

-0.42

mvn

-0.42

addLast

-0.41

Skocz

-0.40

дви

-0.40

jug

-0.39

POSITIVE LOGITS

IntoConstraints

0.80

 uint

0.80

 SPDX

0.72

uint

0.71

TagMode

0.71

AndEndTag

0.71

Initializable

0.70

[](

0.70

олові

0.67

msgSender

0.63

Activations Density 0.033%

elements within structured data and their attributes

No Comments

No Known Activations