INDEX

Explanations

phrases related to establishing relationships or dependencies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Visser

-0.41

 Urteil

-0.41

mė

-0.40

 Muskel

-0.40

 Barker

-0.39

 menschliche

-0.39

Remembering

-0.39

 Kowal

-0.36

 courants

-0.36

 Ballard

-0.35

POSITIVE LOGITS

把

0.65

AlterField

0.60

将

0.58

awtextra

0.56

把

0.53

将

0.53

將

0.52

strictEqual

0.51

peq

0.48

要把

0.48

Activations Density 1.270%

phrases related to establishing relationships or dependencies

No Comments

No Known Activations