INDEX

Explanations

elements related to randomness and randomness-based processes in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-0.77

RenderAtEndOf

-0.73

 cdti

-0.66

 jScrollPane

-0.62

idać

-0.61

 surla

-0.61

 itſelf

-0.60

 Cushing

-0.60

')['

-0.59

 Monfieur

-0.59

POSITIVE LOGITS

 random

2.95

 Random

2.65

Random

2.63

random

2.60

 randomly

2.58

 RANDOM

2.40

RANDOM

2.17

随机

2.16

 randomness

2.00

 rand

1.90

Activations Density 0.463%

elements related to randomness and randomness-based processes in programming contexts

No Comments

No Known Activations