INDEX

Explanations

non-verbal or undefined identifiers commonly used in programming or data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

HtmlAttribute

-0.56

níky

-0.52

LogFactory

-0.52

DoubleQuotes

-0.51

 kartą

-0.49

 Bent

-0.48

 Skinny

-0.47

 darker

-0.47

fony

-0.47

 HttpNotFound

-0.46

POSITIVE LOGITS

WEBPACK

0.87

 propOrder

0.85

LookAnd

0.82

 Приступљено

0.81

expandindo

0.77

 protoimpl

0.75

AddAttribute

0.75

 AssemblyProduct

0.73

toEqual

0.72

原始内容存档于

0.72

Activations Density 0.030%

non-verbal or undefined identifiers commonly used in programming or data structures

No Comments

No Known Activations