INDEX

Explanations

mathematical notation and symbols related to linear algebra and matrix operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 createState

-0.70

IsContent

-0.61

 jsPsych

-0.59

 Persona

-0.54

torque

-0.53

WSGI

-0.53

īts

-0.52

 muualla

-0.51

Challenges

-0.51

MultipartFile

-0.51

POSITIVE LOGITS

AB

0.98

AB

0.98

ABC

0.93

ab

0.91

xy

0.89

ab

0.88

abc

0.88

ijk

0.87

abc

0.85

ABC

0.85

Activations Density 1.560%

mathematical notation and symbols related to linear algebra and matrix operations

No Comments

No Known Activations