INDEX

Explanations

features related to product design and comfort

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 incompetence

-0.56

expandindo

-0.55

 XCTest

-0.54

 MaterialApp

-0.53

HomeAsUp

-0.52

 فريبيس

-0.52

DockStyle

-0.51

 thiệu

-0.51

 Karachi

-0.51

 EconPapers

-0.50

POSITIVE LOGITS

antaranya

0.61

はじめに

0.59

czegóły

0.56

CrossRef

0.54

lielmo

0.53

<bos>

0.53

 Wikiseite

0.51

requestCode

0.51

LabelTagHelper

0.51

ighthouse

0.50

Activations Density 0.344%

features related to product design and comfort

No Comments

No Known Activations