INDEX

Explanations

terms related to medication and biological processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-1.25

存于互联网档案馆

-1.16

 CreateTagHelper

-1.16

AutoScaleMode

-1.15

 nahilalakip

-1.13

 Rasp

-1.10

IUrlHelper

-1.09

LEncoder

-1.09

GEBURTS

-1.09

})*/

-1.08

POSITIVE LOGITS

1.74

1.64

1.57

1.54

1.35

ه

1.19

1.09

er

1.01

ی

0.98

en

0.95

Activations Density 2.243%

terms related to medication and biological processes

No Comments

No Known Activations