INDEX

Explanations

parameters and interpretations related to study data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yntaxException

-0.50

#+#

-0.45

imread

-0.44

tagHelperRunner

-0.44

ErrUnexpectedEOF

-0.43

󠁴

-0.43

WithIOException

-0.43

thâu

-0.41

QMetaType

-0.41

 NSError

-0.40

POSITIVE LOGITS

KURZBESCHREIBUNG

0.57

 Reverso

0.48

 name

0.47

</thead>

0.47

RunWith

0.47

colhead

0.45

lewati

0.45

MBOL

0.43

istung

0.43

name

0.43

Activations Density 0.436%

parameters and interpretations related to study data

No Comments

No Known Activations