INDEX

Explanations

technical jargon and complex terms associated with software or hardware

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTSDATUM

-1.00

ymce

-0.86

principalTable

-0.85

erializer

-0.84

IPAC

-0.84

>{@

-0.83

PerformLayout

-0.80

 ✭✭

-0.76

mobileqq

-0.76

曖昧さ回避

-0.76

POSITIVE LOGITS

 itſelf

1.09

 myſelf

1.09

 Jefus

1.09

 Majefty

1.08

 whoſe

1.08

 ſtate

1.08

 himſelf

1.03

 themſelves

1.01

 becauſe

1.01

 Reſ

1.00

Activations Density 2.583%

technical jargon and complex terms associated with software or hardware

No Comments

No Known Activations