INDEX

Explanations

references to scientific instruments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Efq

-1.21

 NSCoder

-1.12

XmlAccessType

-1.04

 Cæsar

-0.96

 Majefty

-0.95

olesale

-0.94

 snippetHide

-0.94

 Reſ

-0.91

 propOrder

-0.91

^(@)

-0.90

POSITIVE LOGITS

 instrument

0.92

instrument

0.86

Instrument

0.81

 Instrument

0.80

 INSTRUMENT

0.70

 instrumental

0.69

Instrumental

0.60

 instruments

0.58

Named

0.58

instrumental

0.58

Activations Density 0.107%

references to scientific instruments

No Comments

No Known Activations