INDEX

Explanations

references to quantity or number of occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Slf

-0.77

 tasche

-0.73

 vertes

-0.69

 esetén

-0.69

 digitais

-0.68

לית

-0.66

 laikā

-0.63

 bolig

-0.62

yra

-0.61

 grafica

-0.61

POSITIVE LOGITS

 dozen

1.23

few

1.06

dozen

1.02

FEW

1.00

 hundred

0.95

 wenige

0.94

 CreateTagHelper

0.92

few

0.90

FieldBuilder

0.88

 wenigen

0.85

Activations Density 0.072%

references to quantity or number of occurrences

No Comments

No Known Activations