INDEX

Explanations

technical terms and identifiers related to system processes and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 AssemblyCompany

-0.76

InitVars

-0.72

PreExecute

-0.65

 springfox

-0.62

 defaultstate

-0.59

 esboço

-0.59

цездатний

-0.58

SerializedSize

-0.57

AntiForgeryToken

-0.57

 <>",

-0.56

POSITIVE LOGITS

 longevity

0.76

WriteTagHelper

0.74

persistence

0.71

 continuity

0.68

 Repeated

0.68

 repeated

0.67

 Repeat

0.65

 repeat

0.64

Repeat

0.63

ongevity

0.62

Activations Density 0.860%

technical terms and identifiers related to system processes and attributes

No Comments

No Known Activations