INDEX

Explanations

numbers and specific dates

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

Months of the year

np_acts-logits-general · gemini-2.0-flash

months of the year

np_acts-logits-general · gemini-2.5-flash-lite

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

\}\\

-0.57

yarnpkg

-0.55

$$

-0.47

twimg

-0.47

ativement

-0.47

ща

-0.45

}},\

-0.44

 szóci

-0.44

🇻

-0.44

 nogen

-0.44

POSITIVE LOGITS

 April

0.96

 October

0.96

 September

0.95

 February

0.95

 July

0.94

 August

0.94

 June

0.93

 November

0.92

 January

0.89

 March

0.89

Activations Density 0.218%

numbers and specific dates

Months of the year

months of the year

No Comments

No Known Activations