INDEX

Explanations

occurrences of control flow keywords, particularly loops and deletions in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

<%=

-0.53

 mView

-0.53

 pObj

-0.53

⁄

-0.52

"=

-0.50

""

-0.50

 frattempo

-0.49

 isNameExpr

-0.49

'=

-0.48

"")

-0.48

POSITIVE LOGITS

 CreateTagHelper

0.97

enumii

0.92

_,

0.88

 дописавши

0.85

IUrlHelper

0.84

awtextra

0.83

帖最后由

0.81

Personendaten

0.80

BeginInit

0.79

 unknownFields

0.76

Activations Density 0.044%

occurrences of control flow keywords, particularly loops and deletions in code snippets

No Comments

No Known Activations