INDEX

Explanations

nested parentheses and mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Personensuche

-0.89

$")

-0.89

 useAppContext

-0.88

$",

-0.80

]='\

-0.78

SharedDtor

-0.75

)')

-0.73

 Мексичка

-0.73

)"),

-0.73

 <<<<<<<<<<<<<<

-0.71

POSITIVE LOGITS

int

0.73

(((

0.65

(((

0.65

uint

0.63

!(

0.62

float

0.60

*(

0.59

((

0.58

bool

0.56

-(

0.56

Activations Density 0.118%

nested parentheses and mathematical expressions

No Comments

No Known Activations