INDEX

Explanations

sequences of numbers, particularly related to diagnostics or measurements

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

']))

-1.19

 Paglinawan

-1.05

"])

-1.02

']],

-1.00

"]);

-0.97

}</

-0.96

]}>

-0.95

 itſelf

-0.94

}}]{

-0.93

POSITIVE LOGITS

1.32

nd

1.20

1.03

0.99

0.98

0.92

0.91

0.88

0.87

0.83

Activations Density 0.259%

sequences of numbers, particularly related to diagnostics or measurements

No Comments

No Known Activations