INDEX

Explanations

content related to computer software installation and uninstallation processes

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

Tokens starting with "K" followed by another letter

np_acts-logits-general · gemini-2.0-flash

words starting with K

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

CppMethod

-0.48

cirq

-0.46

 Scip

-0.45

ç

-0.44

FetchType

-0.42

 Adama

-0.42

roch

-0.42

umpang

-0.42

RenderAtEndOf

-0.42

Wag

-0.41

POSITIVE LOGITS

KT

1.26

KP

1.25

KC

1.22

KF

1.21

KB

1.20

KM

1.19

KD

1.18

 Kernel

1.16

KI

1.15

 Keyword

1.15

Activations Density 0.749%

content related to computer software installation and uninstallation processes

Tokens starting with "K" followed by another letter

words starting with K

No Comments

No Known Activations