INDEX

Explanations

numerical values associated with object identifiers or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 laude

-0.64

 lenker

-0.59

forRoot

-0.59

AndFlush

-0.59

Referencies

-0.58

AndEndTag

-0.55

Datuak

-0.53

 Hence

-0.53

ukone

-0.52

}';

-0.52

POSITIVE LOGITS

,\\

0.93

0.86

0.80

==",

0.79

,“

0.77

=,

0.77

…,

0.77

,…

0.75

),”

0.74

+',

0.73

Activations Density 0.126%

numerical values associated with object identifiers or attributes

No Comments

No Known Activations