INDEX

Explanations

terms related to statistical metrics and error calculations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 "..\..\

-0.79

 "..\..\..\

-0.64

opaque

-0.63

Demografía

-0.59

TestBed

-0.57

новниш

-0.57

 لينك

-0.57

ilizar

-0.56

 Mitar

-0.54

 webdriver

-0.54

POSITIVE LOGITS

 amplitude

0.87

 magnitude

0.81

 amplitudes

0.75

 Magnitude

0.74

Magnitude

0.71

amplitude

0.71

 magnitudes

0.69

 Amplitude

0.68

magnitude

0.61

 magnitud

0.59

Activations Density 0.657%

terms related to statistical metrics and error calculations

No Comments

No Known Activations