INDEX

Explanations

symbols and formatting used in mathematical or programming notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

[toxicity=0]

-0.98

-0.92

 also

-0.88

is

-0.85

...

-0.84

-0.83

be

-0.80

-0.77

-0.75

POSITIVE LOGITS

<bos>

1.23

ThemeOverlay

1.17

 Савезне

1.17

 kaarangay

1.17

sizeCache

1.16

 Paglinawan

1.08

 Drapeau

1.07

 resourceCulture

1.05

 myſelf

1.00

windowFixed

1.00

Activations Density 5.170%

symbols and formatting used in mathematical or programming notations

No Comments

No Known Activations