INDEX

Explanations

keywords related to read-only attributes or properties

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

ViewFeatures

-0.65

 Italijani

-0.58

 airfoil

-0.57

enterOuterAlt

-0.56

-0.55

 jambe

-0.55

inus

-0.54

 übrig

-0.54

tagext

-0.54

くれました

-0.53

POSITIVE LOGITS

 readonly

2.94

readonly

2.42

ReadOnly

1.15

readOnly

1.00

0.85

]];

0.81

 setLoading

0.77

 BufferedReader

0.76

}>;

0.74

 doubtnut

0.72

Activations Density 0.013%

keywords related to read-only attributes or properties

No Comments

No Known Activations