INDEX

Explanations

causal relationships or outcomes associated with events or actions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 estekak

-0.46

Brainz

-0.45

ⓧ

-0.44

IUrlHelper

-0.43

بوابة

-0.43

 склад

-0.43

 Roskov

-0.43

 nerv

-0.42

 AppCompatTheme

-0.42

ár

-0.41

POSITIVE LOGITS

 resulted

1.79

 resulting

1.23

resulting

1.14

 occurred

0.77

 consisted

0.75

 culminated

0.75

 resultar

0.72

 resultant

0.71

 résult

0.69

 résulte

0.67

Activations Density 0.264%

causal relationships or outcomes associated with events or actions

No Known Activations