INDEX

Explanations

code constructs related to functions and session management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 loosely

-0.66

 largely

-0.65

 primarily

-0.62

 slowly

-0.62

 gradually

-0.60

 higher

-0.59

 Aérea

-0.59

 virtually

-0.58

 across

-0.58

bibinfo

-0.57

POSITIVE LOGITS

GEBURTSDATUM

0.90

IsInitialized

0.84

 Meksiku

0.81

sizeCache

0.75

DotNetBar

0.75

featureID

0.73

WebMethod

0.73

tagHelperRunner

0.72

onViewCreated

0.72

parsedMessage

0.71

Activations Density 0.050%

code constructs related to functions and session management

No Comments

No Known Activations