INDEX

Explanations

references to data structures or code elements, particularly in programming or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

AsUp

-0.87

 restTemplate

-0.79

))))))))

-0.73

])));

-0.73

ciutto

-0.73

berti

-0.72

avadoc

-0.72

AAAAAAAAAAAAAAAA

-0.71

 ProtoMessage

-0.70

InputTagHelper

-0.69

POSITIVE LOGITS

ftagPool

0.76

0.75

0.67

 loob

0.65

 Washburn

0.63

 vatt

0.61

Przypisy

0.60

MAXN

0.59

NUMX

0.58

Activations Density 0.199%

references to data structures or code elements, particularly in programming or technical contexts

No Comments

No Known Activations