INDEX

Explanations

references to originality and development of new ideas or creative works

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

 photolibrary

-0.69

PyExc

-0.67

ISupport

-0.62

 EconPapers

-0.61

:\\

-0.60

ValueStyle

-0.59

Sucesor

-0.59

évaluateur

-0.58

 ReactDOM

-0.58

MethodManager

-0.57

POSITIVE LOGITS

 invented

0.85

 created

0.73

 custom

0.71

 devised

0.70

new

0.69

created

0.67

custom

0.66

 Created

0.65

独自

0.65

 proprietary

0.64

Activations Density 0.477%

references to originality and development of new ideas or creative works

No Comments

No Known Activations