INDEX

Explanations

phrases indicating past actions or events that have occurred

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

 actuelles

-0.63

ibouti

-0.60

 présidenti

-0.58

cephala

-0.58

onesia

-0.58

 copertina

-0.58

 copertura

-0.57

 aiuto

-0.57

afu

-0.57

Soma

-0.56

POSITIVE LOGITS

 earlier

1.17

 previously

0.99

earlier

0.96

 hadn

0.91

Earlier

0.90

 Earlier

0.88

 previous

0.85

Previously

0.80

astéroïdes

0.78

 hoped

0.77

Activations Density 0.326%

phrases indicating past actions or events that have occurred

No Comments

No Known Activations