INDEX

Explanations

parts of the document that express a clear observed phenomenon or event

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

setupUi

-0.64

 protoimpl

-0.61

AutoScale

-0.58

 Phry

-0.53

getragen

-0.53

ByteString

-0.53

 Southland

-0.52

Geografi

-0.52

ReadInt

-0.51

 Eura

-0.51

POSITIVE LOGITS

 PyObject

0.71

存于互联网档案馆

0.64

feira

0.60

PyObject

0.59

بوابة

0.59

findpost

0.57

veaux

0.57

 CreateTagHelper

0.56

 CGRectMake

0.54

 intptr

0.53

Activations Density 0.012%

parts of the document that express a clear observed phenomenon or event

No Comments

No Known Activations