INDEX

Explanations

terms related to mathematical concepts, particularly those involving transformations and changes in state

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 CreateTagHelper

-1.03

parsedMessage

-1.00

 nahilalakip

-0.88

RenderAtEndOf

-0.83

webElementXpaths

-0.79

featureID

-0.77

 يتيمه

-0.77

 <=",

-0.75

 estekak

-0.74

الحياه

-0.71

POSITIVE LOGITS

 value

0.26

Ruh

0.25

 insulation

0.25

let

0.24

 word

0.24

 entire

0.24

 effect

0.23

 process

0.23

edm

0.23

支

0.22

Activations Density 0.217%

terms related to mathematical concepts, particularly those involving transformations and changes in state

No Comments

No Known Activations