INDEX

Explanations

mention of family relationships and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

enumi

-0.78

]--;

-0.66

DataSetChanged

-0.57

 holders

-0.55

Hilsen

-0.55

lably

-0.54

ERSHIP

-0.54

unächst

-0.54

bronn

-0.54

 CreateTagHelper

-0.54

POSITIVE LOGITS

 quadrature

0.68

ArgumentParser

0.61

HideFlags

0.59

 snare

0.56

 pettico

0.53

OGND

0.53

তথ্যসূত্র

0.52

 dumbbells

0.51

 oxidase

0.51

 Nether

0.50

Activations Density 0.019%

mention of family relationships and names

No Comments

No Known Activations