INDEX

Explanations

technical terms related to programming or data handling

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

Code, logs, or program snippets

np_acts-logits-general · gemini-2.0-flash

eset

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ConstraintMaker

-1.24

Efq

-1.20

DockStyle

-1.18

 CreateTagHelper

-1.15

 purpoſe

-1.15

AndEndTag

-1.12

 gynhyrchwyd

-1.12

 itſelf

-1.09

principalColumn

-1.09

setVerticalGroup

-1.06

POSITIVE LOGITS

<unused63>

0.38

<unused61>

0.38

0.37

<unused62>

0.36

<unused60>

0.35

["

0.33

 eset

0.33

gef

0.32

ön

0.32

Activations Density 0.141%

technical terms related to programming or data handling

Code, logs, or program snippets

eset

No Comments

No Known Activations