INDEX

Explanations

references to the color blue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

__":

-0.95

 typelib

-0.81

__':

-0.80

 Roskov

-0.80

 propOrder

-0.79

 >=",

-0.78

__':

-0.78

 ostavi

-0.77

__":

-0.77

PreferredItem

-0.76

POSITIVE LOGITS

 Blue

1.38

 BLUE

1.35

 blue

1.32

Blue

1.23

blue

1.20

BLUE

1.20

 azules

1.05

 Blues

1.02

 blues

0.96

Blu

0.95

Activations Density 0.061%

references to the color blue

No Comments

No Known Activations