INDEX

Explanations

occurrences of the term "PS" and its related variations, indicating a focus on specific designations or references

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InputBorder

-0.78

 Cauchy

-0.70

databind

-0.66

 Volker

-0.65

 Rendez

-0.65

 Nazar

-0.65

nF

-0.64

 Melville

-0.64

Hozzáférés

-0.63

 Timor

-0.61

POSITIVE LOGITS

PS

2.27

ps

2.20

PS

2.01

ps

1.85

Ps

1.77

Ps

1.43

PSM

1.42

 PlayStation

1.31

PlayStation

1.23

 Playstation

1.13

Activations Density 0.060%

occurrences of the term "PS" and its related variations, indicating a focus on specific designations or references

No Comments

No Known Activations