INDEX

Explanations

terms related to biochemical processes involving hormones and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/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.33.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

存于互联网档案馆

-0.43

 Roskov

-0.43

GIVEREF

-0.42

chauss

-0.40

 niech

-0.40

 PrintWriter

-0.39

 InputDecoration

-0.39

Ārējās

-0.39

styleType

-0.38

தல்

-0.38

POSITIVE LOGITS

 peptide

1.42

 peptides

1.34

 Peptide

1.30

Peptide

1.23

peptide

1.16

Pep

1.16

Pep

1.09

肽

1.05

pep

1.03

pep

1.02

Activations Density 0.990%

terms related to biochemical processes involving hormones and their effects

No Comments

No Known Activations