INDEX

Explanations

text related to scientific terms or formal structures in documents

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

]--;

-0.95

Brainz

-0.84

"):

-0.76

$',

-0.69

nemies

-0.69

{*}

-0.68

存于互联网档案馆

-0.68

Datuak

-0.68

"]),

-0.67

}]{

-0.67

POSITIVE LOGITS

0.54

0.53

0.52

ul

0.51

0.50

du

0.50

0.49

Activations Density 0.280%

text related to scientific terms or formal structures in documents

No Comments

No Known Activations