INDEX

Explanations

references to software updates and versions in technical documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

 muñeca

-0.63

 Füße

-0.61

rungsseite

-0.60

 Sünden

-0.60

 kautta

-0.60

 muñecas

-0.59

 Sünde

-0.58

 Gefühle

-0.57

 pegatinas

-0.56

 Geschichts

-0.55

POSITIVE LOGITS

 Photoshop

0.89

 Microsoft

0.79

 Adobe

0.77

 Matlab

0.77

 Google

0.77

 MATLAB

0.75

 Windows

0.72

 Python

0.72

 WordPress

0.72

 photoshop

0.71

Activations Density 1.631%

references to software updates and versions in technical documentation

No Comments

No Known Activations