INDEX

Explanations

important descriptors or attributes of features or events

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Clik

-0.54

 مرئيه

-0.52

 rispet

-0.50

AccessorTable

-0.49

 préc

-0.48

umesc

-0.48

retario

-0.47

 analogues

-0.46

 GenerationType

-0.46

 lượt

-0.46

POSITIVE LOGITS

 feature

1.52

 trait

1.31

feature

1.23

 phenomenon

1.20

 aspect

1.16

 tactic

1.15

 thing

1.13

 attribute

1.12

 option

1.12

 requirement

1.10

Activations Density 1.402%

important descriptors or attributes of features or events

No Comments

No Known Activations