INDEX

Explanations

words related to disks, particularly in scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 artefacts

-1.13

 moulds

-1.10

 Colours

-1.09

 nahilalakip

-1.08

]',

-1.06

 licences

-1.05

 enquiries

-1.02

 '../../../../

-1.02

 tonnes

-1.01

Colours

-1.00

POSITIVE LOGITS

 theaters

1.21

 gages

1.14

 disks

1.13

 viață

1.11

și

1.07

Theater

1.07

 Theaters

1.07

 theater

1.05

 fibers

1.05

 Theater

1.03

Activations Density 1.894%

words related to disks, particularly in scientific or technical contexts

No Comments

No Known Activations