INDEX

Explanations

code snippets and constructs related to defining and using variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 toni

-0.54

FailureListener

-0.53

spesies

-0.51

 đăng

-0.51

mulo

-0.50

 ağı

-0.49

ंदीखरीदारी

-0.49

ValueStyle

-0.48

estors

-0.48

ResumeLayout

-0.48

POSITIVE LOGITS

 ModelExpression

1.03

useState

0.69

StringVar

0.67

GEBURTSDATUM

0.67

 useState

0.67

 StringVar

0.66

ManagedBean

0.66

HideInInspector

0.65

 variables

0.65

 createContext

0.61

Activations Density 1.010%

code snippets and constructs related to defining and using variables

No Comments

No Known Activations