INDEX

Explanations

terms related to the prefix "hom" and its variations, typically associated with concepts in science and medicine

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

WebControls

-0.63

nodoc

-0.59

Portail

-0.56

Portale

-0.55

DataAnnotations

-0.53

siger

-0.50

 soñar

-0.50

RegisterType

-0.50

ngths

-0.49

FDRE

-0.49

POSITIVE LOGITS

DIPSETTING

0.60

OGND

0.59

ARANCE

0.58

Yom

0.55

bination

0.53

InputBorder

0.53

blumen

0.53

 Ом

0.53

BOM

0.52

 Smol

0.51

Activations Density 0.179%

terms related to the prefix "hom" and its variations, typically associated with concepts in science and medicine

No Comments

No Known Activations