INDEX

Explanations

references to archaeological findings and artifacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

NewReader

-0.53

acağı

-0.51

 Almanac

-0.50

pacs

-0.49

 personnalisés

-0.47

 paesi

-0.47

byshev

-0.47

->$

-0.47

věř

-0.46

 상세

-0.46

POSITIVE LOGITS

 finds

0.81

 excavated

0.79

Dating

0.76

 fragmentary

0.75

 evidence

0.75

finds

0.72

 archaeological

0.71

 excavations

0.71

 remains

0.71

 Finds

0.70

Activations Density 0.239%

references to archaeological findings and artifacts

No Comments

No Known Activations