INDEX

Explanations

elements related to programming and data handling

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

Code or identifiers within text

np_acts-logits-general · gemini-2.0-flash

update command

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

↵↵

-0.75

<eos>

-0.66

<bos>

-0.63

-0.59

-0.58

↵

-0.57

.-

-0.56

-0.54

-0.53

POSITIVE LOGITS

tagHelperRunner

1.42

AndEndTag

1.35

 الرياضيه

1.34

PerformLayout

1.31

StoryboardSegue

1.27

tvguidetime

1.25

principalColumn

1.23

RenderAtEndOf

1.23

featureID

1.22

 مشين

1.21

Activations Density 0.313%

elements related to programming and data handling

Code or identifiers within text

update command

No Comments

No Known Activations