INDEX

Explanations

references to randomness in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 وتسجيلات

-0.67

 InputDecoration

-0.64

InjectAttribute

-0.62

oneph

-0.62

 protoimpl

-0.60

 GoogleFonts

-0.59

'>=

-0.58

Награды

-0.58

 متحده

-0.57

GTI

-0.55

POSITIVE LOGITS

 azar

0.87

 RANDOM

0.84

RANDOM

0.83

 randomly

0.83

 rand

0.79

 Random

0.78

 random

0.74

 Ramb

0.72

 randomness

0.69

Random

0.69

Activations Density 0.192%

references to randomness in various contexts

No Comments

No Known Activations