INDEX

Explanations

terms related to hormones and their functions

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

hormones

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 Dead

-0.45

view

-0.42

View

-0.42

 échanti

-0.42

 Siete

-0.41

VIEW

-0.41

sample

-0.41

 Putih

-0.41

 View

-0.41

++]=

-0.41

POSITIVE LOGITS

 Hormones

1.10

 Hormone

1.05

 hormones

1.02

 hormone

1.02

 hormonal

0.97

Horm

0.92

 Horm

0.84

horm

0.84

 hormon

0.77

激素

0.69

Activations Density 0.011%

terms related to hormones and their functions

hormones

No Comments

No Known Activations