INDEX

Explanations

mathematical notation and sequences

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

">//

-0.76

abestanden

-0.70

ulipas

-0.70

 للاسماء

-0.69

]();

-0.67

 OMITBAD

-0.67

 beginnetje

-0.67

 estimés

-0.66

 חיצוניים

-0.66

 Lightboxes

-0.65

POSITIVE LOGITS

AlterField

0.49

 single

0.48

 Füßen

0.47

种

0.46

 Bere

0.46

tacle

0.45

interopRequire

0.45

dymyr

0.45

RIED

0.44

ixeira

0.43

Activations Density 1.264%

mathematical notation and sequences

No Comments

No Known Activations