INDEX

Explanations

programming-related terms and functions

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

Code snippets or file extensions

np_acts-logits-general · gemini-2.0-flash

template files and rendering

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

writeFieldEnd

-0.64

AsUp

-0.61

 kasarigan

-0.57

uestamente

-0.54

MethodManager

-0.52

DBNull

-0.50

raszamy

-0.50

principalColumn

-0.50

amzn

-0.49

ksom

-0.48

POSITIVE LOGITS

 template

1.52

 templates

1.38

 Template

1.37

template

1.33

Template

1.30

 Templates

1.25

 TEMPLATE

1.24

模板

1.23

 模板

1.21

templates

1.11

Activations Density 0.278%

programming-related terms and functions

Code snippets or file extensions

template files and rendering

No Comments

No Known Activations