INDEX

Explanations

programming and coding terminology

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

TagMode

-1.20

VersionUID

-1.15

 ModelExpression

-1.01

DockStyle

-0.82

findpost

-0.81

HideFlags

-0.81

yntaxException

-0.80

IndentedString

-0.78

 CreateTagHelper

-0.76

ContentAsync

-0.76

POSITIVE LOGITS

enc

1.07

enc

0.81

Enc

0.72

Enc

0.65

ENC

0.59

INC

0.59

 Wikimedijinoj

0.58

pyl

0.58

ENC

0.55

 cister

0.55

Activations Density 0.017%

programming and coding terminology

No Comments

No Known Activations