INDEX

Explanations

sections that outline goals, components, and descriptions in a document

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

Lie

-0.36

Lie

-0.36

sequ

-0.35

.*")]

-0.35

 subjective

-0.34

 sequ

-0.34

etc

-0.34

alas

-0.34

Sie

-0.34

拿

-0.34

POSITIVE LOGITS

ReusableCell

0.86

 doInBackground

0.82

oa̍t

0.82

featureID

0.67

 OFDb

0.58

 estekak

0.58

SequentialGroup

0.58

 Савезне

0.57

 ब्रेकडाउन

0.57

 ProtoMessage

0.57

Activations Density 0.794%

sections that outline goals, components, and descriptions in a document

No Comments

No Known Activations