INDEX

Explanations

terms related to errors and failures in processes

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

)");

-1.14

"},

-1.12

});*/

-1.11

)";

-1.11

"],

-1.05

'],

-1.04

`,

-1.02

'},

-1.02

})*/

-1.01

":

-0.98

POSITIVE LOGITS

0.88

 please

0.78

!!

0.75

!!!

0.68

please

0.68

 Please

0.65

Please

0.63

0.62

0.61

!!!!

0.59

Activations Density 0.262%

terms related to errors and failures in processes

No Comments

No Known Activations