INDEX

Explanations

numerical values and mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ức

-0.44

&_

-0.43

}}-\

-0.41

ometro

-0.40

&_

-0.39

$_.

-0.39

atim

-0.38

voll

-0.38

MouseAdapter

-0.38

Географија

-0.37

POSITIVE LOGITS

2.07

1.96

$[

1.64

}[

1.47

{[

1.42

.[

1.40

,[

1.40

-[

1.37

?[

1.35

:[

1.34

Activations Density 0.865%

numerical values and mathematical expressions

No Comments

No Known Activations