INDEX

Explanations

numerical data or symbols related to measurements and results in scientific contexts

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

InteropServices

-0.50

Eyed

-0.49

ContainsKey

-0.47

-0.46

®

-0.45

~\

-0.45

weiser

-0.44

POSITIVE LOGITS

 '\\;'

1.15

 kasarigan

1.04

$)$

1.01

SourceChecksum

0.98

 مشين

0.96

MigrationBuilder

0.94

:✨

0.94

 estekak

0.88

findpost

0.86

Activations Density 0.254%

numerical data or symbols related to measurements and results in scientific contexts

No Comments

No Known Activations