INDEX

Explanations

references to academic publications and specific journals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

+#+

-0.40

 timpul

-0.40

"}")

-0.38

})`

-0.36

gó

-0.36

 urma

-0.34

effetto

-0.34

principalColumn

-0.33

estinal

-0.33

dflare

-0.33

POSITIVE LOGITS

 IEEE

0.77

IEEE

0.64

 насељу

0.63

 defStyle

0.56

 ieee

0.52

adeloupe

0.50

chartInstance

0.49

ieee

0.49

ziasztok

0.48

Cordialement

0.45

Activations Density 0.412%

references to academic publications and specific journals

No Comments

No Known Activations