INDEX

Explanations

references to works or categories in various classifications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 kaynağından

-0.65

Према

-0.50

 serons

-0.45

pytest

-0.43

setClass

-0.43

[*]

-0.42

tadır

-0.41

щото

-0.41

ificantly

-0.41

 Процитовано

-0.41

POSITIVE LOGITS

]--;

0.96

 autorytatywna

0.87

LayoutConstraint

0.79

Personendaten

0.78

ValueGeneration

0.77

TagHelpers

0.76

elemField

0.74

thâu

0.73

 समीक्षक

0.70

verwijspagina

0.70

Activations Density 1.062%

references to works or categories in various classifications

No Comments

No Known Activations