INDEX

Explanations

mathematical expressions or equations related to specific functions or variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Wikimedijinoj

-1.28

 estekak

-1.28

]")]

-1.20

 pleaſure

-1.16

 leaſt

-1.12

########.

-1.11

 Theſe

-1.09

 Vikipedi

-1.09

 Monfieur

-1.09

 Numerade

-1.08

POSITIVE LOGITS

0.71

0.69

0.64

0.63

0.62

0.60

</i>

0.58

↵

0.56

</em>

0.53

Activations Density 0.345%

mathematical expressions or equations related to specific functions or variables

No Comments

No Known Activations