INDEX

Explanations

specific terms and references from various academic 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 @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Efq

-1.07

 myſelf

-1.03

 Jefus

-0.95

 becauſe

-0.94

 Theſe

-0.93

 himſelf

-0.88

 poffible

-0.87

 ſeveral

-0.86

 whoſe

-0.86

 Shaksp

-0.85

POSITIVE LOGITS

NameInMap

0.64

rungsseite

0.56

SourceChecksum

0.55

 back

0.52

enty

0.52

 disambiguazione

0.50

chi

0.49

ThroughAttribute

0.49

pri

0.49

Activations Density 0.145%

specific terms and references from various academic or technical contexts

No Comments

No Known Activations