INDEX

Explanations

boolean expressions indicating the presence or absence of certain values or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

fjspx

-0.84

存于互联网档案馆

-0.82

tonsoft

-0.75

:+:

-0.74

TagMode

-0.73

dafx

-0.70

RegistryLite

-0.68

MLLoader

-0.66

Efq

-0.65

 виправивши

-0.65

POSITIVE LOGITS

getBoolean

0.67

 boolean

0.60

BooleanField

0.60

Boolean

0.58

boolean

0.58

bool

0.57

stdbool

0.56

 bool

0.54

False

0.54

putBoolean

0.54

Activations Density 0.918%

boolean expressions indicating the presence or absence of certain values or states

No Comments

No Known Activations