INDEX

Explanations

terms related to hormones and their regulatory effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Virtu

-0.55

 viewType

-0.54

óch

-0.51

大

-0.48

Vir

-0.48

yers

-0.48

 vong

-0.48

 laptop

-0.48

 Laptop

-0.47

 kred

-0.47

POSITIVE LOGITS

 hormones

1.25

 Hormones

1.15

 hormone

1.14

Horm

1.03

 hormonal

1.02

complexContent

1.02

 Hormone

1.00

horm

0.98

 endocrine

0.91

 hormon

0.90

Activations Density 0.818%

terms related to hormones and their regulatory effects

No Comments

No Known Activations

terms related to hormones and their regulatory effects

No Comments

No Known Activations