INDEX

Explanations

specific formatting or structure within code and data

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

Code with numbers, operators, and symbols

np_acts-logits-general · gemini-2.0-flash

code syntax and symbols

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

-0.56

 propOrder

-0.51

-0.49

</strong>

-0.47

...

-0.47

,*

-0.46

<eos>

-0.45

-0.44

…

-0.44

-0.43

POSITIVE LOGITS

Efq

0.90

 myſelf

0.75

 Theſe

0.73

 purpoſe

0.72

IsContent

0.72

 Constants

0.72

 poffe

0.70

 poffible

0.69

 ſche

0.69

 houſe

0.69

Activations Density 0.519%

specific formatting or structure within code and data

Code with numbers, operators, and symbols

code syntax and symbols

No Comments

No Known Activations