INDEX

Explanations

programming keywords and structural elements within code

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

Variable or parameter declarations

np_acts-logits-general · gemini-2.0-flash

private member declarations

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

<bos>

-0.61

///</

-0.60

GeoNames

-0.57

 sarili

-0.56

 acestei

-0.54

 ©️

-0.54

,"

-0.53

 незавершена

-0.50

,'

-0.49

##

-0.49

POSITIVE LOGITS

 bool

1.14

 boolean

1.11

int

1.07

bool

1.00

boolean

0.89

int

0.86

 float

0.77

AndEndTag

0.74

float

0.67

 string

0.66

Activations Density 0.121%

programming keywords and structural elements within code

Variable or parameter declarations

private member declarations

No Comments

No Known Activations