INDEX

Explanations

terms related to medical conditions, their symptoms, and associated treatments

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

before "state" or related to states of things

np_acts-logits-general · gemini-2.0-flash

names followed by specific types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/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.24.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

didSet

-0.46

 grotes

-0.38

Studies

-0.31

postolic

-0.30

 Unsc

-0.30

וע

-0.29

 regel

-0.28

 surla

-0.28

 spä

-0.28

Its

-0.28

POSITIVE LOGITS

 appunto

0.66

 CreateTagHelper

0.65

 resourceCulture

0.64

+#+#

0.62

 autorytatywna

0.61

mybatisplus

0.60

complexContent

0.60

andExpect

0.57

 jLabel

0.56

 chi̍t

0.55

Activations Density 0.652%

terms related to medical conditions, their symptoms, and associated treatments

before "state" or related to states of things

names followed by specific types

No Comments

No Known Activations