INDEX

Explanations

occurrences of specific syntax or programming constructs

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

MENAFN

-0.67

 cérami

-0.63

 Thin

-0.57

Thin

-0.57

baguna

-0.55

 مشين

-0.55

gyz

-0.54

lán

-0.54

 žá

-0.53

 mécanisme

-0.52

POSITIVE LOGITS

awtextra

0.69

 utafitiHapana

0.63

DispatchToProps

0.61

inclusion

0.53

 timedelta

0.53

Obrázky

0.52

encodeWith

0.52

Portale

0.51

]-->

0.51

cgi

0.51

Activations Density 0.102%

occurrences of specific syntax or programming constructs

No Comments

No Known Activations