INDEX

Explanations

references to binary variables and causal effects in statistical models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 surla

-0.73

ientôt

-0.71

sizeCache

-0.70

 يتيمه

-0.68

 itſelf

-0.67

 purpoſe

-0.65

 Jefus

-0.65

 pleaſure

-0.65

 themſelves

-0.65

 Gyro

-0.65

POSITIVE LOGITS

CompoundButton

0.84

Boolean

0.80

boolean

0.78

 Boolean

0.76

 boolean

0.73

getBoolean

0.72

BOOLEAN

0.69

bool

0.67

putBoolean

0.67

JCheckBox

0.66

Activations Density 0.818%

references to binary variables and causal effects in statistical models

No Comments

No Known Activations