INDEX

Explanations

references to graphics-related terms or concepts, particularly related to OpenGL

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 defaultstate

-0.85

 AssemblyCompany

-0.62

InjectAttribute

-0.61

HandlerContext

-0.57

rcParams

-0.55

#+#

-0.52

oblig

-0.51

DebuggerNonUser

-0.51

 zone

-0.51

ServletConfig

-0.50

POSITIVE LOGITS

gl

0.96

nl

0.77

NL

0.74

GL

0.73

endphp

0.70

gl

0.66

 ModelExpression

0.65

 consultato

0.65

 fréquent

0.65

 Hernando

0.63

Activations Density 0.116%

references to graphics-related terms or concepts, particularly related to OpenGL

No Comments

No Known Activations