INDEX

Explanations

terms related to the action of extraction in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-1.62

 itſelf

-1.48

 Monfieur

-1.46

 Jefus

-1.39

Efq

-1.38

 themſelves

-1.36

 poffible

-1.32

 himſelf

-1.31

 Theſe

-1.29

 pleaſure

-1.28

POSITIVE LOGITS

 extract

1.19

 Extract

0.95

Extract

0.92

extract

0.91

0.88

0.82

0.79

 extracted

0.78

 extracting

0.74

Activations Density 0.363%

terms related to the action of extraction in various contexts

No Comments

No Known Activations