INDEX

Explanations

references to events and actions related to organization and participation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

igshid

-0.76

เหล

-0.58

 derer

-0.57

 CURIAM

-0.54

protoimpl

-0.53

 These

-0.52

matmul

-0.52

its

-0.50

omotor

-0.49

 isomorphism

-0.49

POSITIVE LOGITS

ValueStyle

0.79

 disambiguazione

0.68

Ecotoxicity

0.65

medim

0.65

 doInBackground

0.63

 <>",

0.62

 proceedings

0.60

 kyse

0.59

>*/

0.59

mtrl

0.58

Activations Density 0.471%

references to events and actions related to organization and participation

No Comments

No Known Activations